@book{CTT100715080, author = {Takao Kobayashi}, title = {Prosody Control and Variation Enhancement Techniques for HMM-Based Expressive Speech Synthesis}, publisher = {Springer}, year = 2015, } @book{CTT100715085, author = {小林 隆夫 and 高木 茂孝}, title = {ディジタル集積回路入門}, publisher = {朝倉書店}, year = 2014, } @book{CTT100605486, author = {Takao Kobayashi}, title = {Speech Signal Processing Toolkit (SPTK)}, publisher = {Consideration Books}, year = 2010, } @book{CTT100526257, author = {小林隆夫（分担） and 広瀬啓吉編著}, title = {韻律と音声言語情報処理}, publisher = {丸善}, year = 2006, } @book{CTT100394238, author = {小林隆夫（分担） and 人工知能学会編}, title = {人工知能学辞典}, publisher = {共立出版}, year = 2005, } @book{CTT100501470, author = {小林隆夫}, title = {スペクトル解析ハンドブック（分担）}, publisher = {朝倉書店}, year = 2004, } @book{CTT100394169, author = {S. Kawamoto and H. Shimodaira and T. Nitta and T. Nishimoto and S. Nakamura and K. Itou and S. Morishima and T. Yotsukura and A. Kai and A. Lee and Y. Yamashita and T. Kobayashi and et al.}, title = {Galatea: Open-source software for developing anthropomorphic spoken dialog agents, in Life-Like Characters: Tools, Affective Functions, and Applications}, publisher = {Springer}, year = 2004, } @book{CTT100538954, author = {小林隆夫}, title = {新版音響用語辞典（分担）}, publisher = {コロナ社}, year = 2003, } @book{CTT100430152, author = {小林 隆夫 and 高木 茂孝}, title = {ディジタル集積回路入門}, publisher = {昭晃堂}, year = 2000, } @article{CTT100815907, author = {Tomoki Koriyama and Takao Kobayashi}, title = {Statistical parametric speech synthesis using deep Gaussian processes}, journal = {IEEE/ACM Transaction on Audio, Speech, and Language Processing}, year = 2019, } @article{CTT100767017, author = {Decha Moungsri and Tomoki Koriyama and Takao Kobayashi}, title = {GPR-based Thai speech synthesis using multi-level duration prediction}, journal = {Speech Communication}, year = 2018, } @article{CTT100745524, author = {Takashi Nose and Yusuke Arao and Takao Kobayashi and Komei Sugiura and Yoshinori Shiga}, title = {Sentence selection based on extended entropy using phonetic and prosodic contexts for statistical paramaetric speech synthesis}, journal = {IEEE/ACM Transaction on Audio, Speech, and Language Processing}, year = 2017, } @article{CTT100737522, author = {長濱大樹 and 能勢 隆 and 郡山知樹 and 小林隆夫}, title = {クロスリンガル音声合成のための共有決定木コンテクストクラスタリングを用いた話者適応}, journal = {電子情報通信学会論文誌D}, year = 2017, } @article{CTT100703188, author = {Takashi Nose and Misa Kanemoto and Tomoki Koriyama and Takao Kobayashi}, title = {HMM-based expressive singing voice synthesis with singing style control and robust pitch modeling}, journal = {Computer Speech & Language}, year = 2015, } @article{CTT100668101, author = {Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {Statistical Parametric Speech Synthesis Based on Gaussian Process Regression}, journal = {IEEE Journal of Selected Topics in Signal Processing}, year = 2014, } @article{CTT100770753, author = {Takashi Nose and Vataya Chunwijitra and Takao Kobayashi}, title = {A Parameter Generation Algorithm Using Local Variance for HMM-Based Speech Synthesis}, journal = {IEEE Journal of Selected Topics in Signal Processing}, year = 2014, } @article{CTT100668122, author = {Yu Maeno and Takashi Nose and Takao Kobayashi and Tomoki Koriyama and Yusuke Ijima and Hideharu Nakajima and Hideyuki Mizuno and Osamu Yoshioka}, title = {Prosodic Variation Enhancement Using Unsupervised Context Labeling for HMM-based Expressive Speech Synthesis}, journal = {Speech Communication}, year = 2014, } @article{CTT100648143, author = {Takashi Nose and Takao Kobayashi}, title = {An intuitive style control technique in HMM-based expressive speech synthesis using subjective style intensity and multiple-regression global variance model}, journal = {Speech Communication}, year = 2013, } @article{CTT100634462, author = {郡山知樹 and 能勢 隆 and 小林 隆夫}, title = {HMMに基づく対話音声合成における多様な韻律生成のためのコンテクストの拡張}, journal = {電子情報通信学会論文誌}, year = 2012, } @article{CTT100632404, author = {Takashi Nose and Takao Kobayashi}, title = {Very low bit-rate F0 coding for phonetic vocoders using MSD-HMM with quantized F0 symbols}, journal = {Speech Communication}, year = 2012, } @article{CTT100632403, author = {Vataya Chunwijitra and Takashi Nose and Takao Kobayashi}, title = {A tone-modeling technique using a quantized F0 context to improve tone correctness in average-voice-based speech synthesis}, journal = {Speech Communication}, year = 2012, } @article{CTT100623982, author = {Takashi Nose and Takao Kobayashi}, title = {Speaker-independent HMM-based voice conversion using adaptive quantization of the fundamental frequency}, journal = {Speech Communication}, year = 2011, } @article{CTT100611747, author = {Takashi Nose and Yuhei Ota and Takao Kobayashi}, title = {HMM-based voice conversion using quantized F0 context}, journal = {IEICE Trans. on Information and Systems}, year = 2010, } @article{CTT100597276, author = {Takashi Nose and Takao Kobayashi}, title = {A technique for estimating intensity of emotional expressions and speaking styles in speech based on multiple-regression HSMM}, journal = {IEICE Trans. on Information and Systems}, year = 2010, } @article{CTT100597275, author = {Yusuke Ijima and Takashi Nose and Makoto Tachibana and Takao Kobayashi}, title = {A rapid model adaptation technique for emotional speech recognition with style estimation based on multiple-regression HMM}, journal = {IEICE Trans. on Information and Systems}, year = 2010, } @article{CTT100572441, author = {Suphattharachai Chomphan and Takao Kobayashi}, title = {Tone correctness improvement in speaker-independent average-voice-based Thai speech synthesis}, journal = {Speech Communication}, year = 2009, } @article{CTT100572442, author = {Takashi Nose and Makoto Tachibana and Takao Kobayashi}, title = {HMM-based style control for expressive speech synthesis with arbitrary speaker's voice using model adaptation}, journal = {IEICE Trans. on Information and Systems}, year = 2009, } @article{CTT100572455, author = {Junichi Yamagishi and Takao Kobayashi and Yuji Nakano and Katsumi Ogata and Juri Isogai}, title = {Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm}, journal = {IEEE Trans. on Audio, Speech, and Language Processing}, year = 2009, } @article{CTT100572433, author = {市川清人 and 三田雄志 and 堀 修 and 小林隆夫}, title = {顔パーツを利用した隠れを含む顔の検出方法}, journal = {画像電子学会誌}, year = 2008, } @article{CTT100572431, author = {Junichi Yamagishi and Hisashi Kawai and Takao Kobayashi}, title = {Phone duration modeling using gradient tree boosting}, journal = {Speech Communication}, year = 2008, } @article{CTT100572432, author = {Suphattharachai Chomphan and Takao Kobayashi}, title = {Tone correctness improvement in speaker dependent HMM-based Thai speech synthesis}, journal = {Speech Communication}, year = 2008, } @article{CTT100572382, author = {Suphattharachai Chomphan and Takao Kobayashi}, title = {Incorporation of phrase intonation to context clustering for average voice models in HMM-based Thai speech synthesis}, journal = {Proc. 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2008, } @article{CTT100572380, author = {Kiyoto Ichikawa and Takeshi Mita and Osamu Hori and Takao Kobayashi}, title = {Component-based face detection method for various types of occluded faces}, journal = {Proc. 2008 3rd International Symposium on Communications, Control, and Signal Processing}, year = 2008, } @article{CTT100550521, author = {Takashi Nose and Junichi Yamagishi and Takashi Masuko and Takao Kobayashi}, title = {A style control technique for HMM-based expressive speech synthesis}, journal = {IEICE Trans. on Information and Systems}, year = 2007, } @article{CTT100550517, author = {Makoto Tachibana and Keigo Kawashima and Junichi Yamagishi and Takao Kobayashi}, title = {Performance evaluation of HMM-based style classification with a small amount of training data}, journal = {Proc. 8th Annual Conference of the International Speech Communication Association}, year = 2007, } @article{CTT100550515, author = {Suphattharachai Chomphan and Takao Kobayashi}, title = {Implementation and evaluation of an HMM-based Thai speech synthesis system}, journal = {Proc. 8th Annual Conference of the International Speech Communication Association}, year = 2007, } @article{CTT100550520, author = {Heiga Zen and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {A Hidden semi-Markov model-based speech synthesis system}, journal = {IEICE Trans. on Information and Systems}, year = 2007, } @article{CTT100550511, author = {Junichi Yamagishi and Takao Kobayashi and Makoto Tachibana and Katsumi Ogata and Yuji Nakano}, title = {Model adaptation approach to speech synthesis with diverse voices and styles}, journal = {Proc. 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2007, } @article{CTT100550519, author = {Heiga Zen and Takashi Masuko and Keiichi Tokuda and Takashi Yoshimura and Takao Kobayashi and Tadashi Kitamura}, title = {State duration modeling for HMM-based speech synthesis}, journal = {IEICE Trans. on Information and Systems}, year = 2007, } @article{CTT100550518, author = {Junichi Yamagishi and Takao Kobayashi}, title = {Average-voice-based speech synthesis using HSMM-based speaker adaptation and adaptive training}, journal = {IEICE Trans. on Information and Systems}, year = 2007, } @article{CTT100526398, author = {Katsumi Ogata and Makoto Tachibana and Junichi Yamagishi and Takao Kobayashi}, title = {Acoustic model training based on linear transformation and MAP modification for HSMM-based speech synthesis}, journal = {Proc. 9th International Conference on Spoken Language Processing}, year = 2006, } @article{CTT100526397, author = {Yuji Nakano and Makoto Tachibana and Junichi Yamagishi and Takao Kobayashi}, title = {Constrained structural maximum a posteriori linear regression for average-voice-based speech synthesis}, journal = {Proc. 9th International Conference on Spoken Language Processing}, year = 2006, } @article{CTT100525445, author = {Junichi Yamagishi and Katsumi Ogata and Yuji Nakano and Juri Isogai and Takao Kobayashi}, title = {HSMM-based model adaptation algorithms for average-voice-based speech synthesis}, journal = {Proc. 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2006, } @article{CTT100525441, author = {Makoto Tachibana and Junichi Yamagishi and Takashi Masuko and Takao Kobayashi}, title = {A style adaptation technique for speech synthesis using HSMM and suprasegmental features}, journal = {IEICE Trans. on Information and Systems}, year = 2006, } @article{CTT100395159, author = {岡崎雅嗣 and 国本利文 and 小林隆夫}, title = {多段スペクトルサブトラクション法を用いた楽音の強調}, journal = {電子情報通信学会論文誌}, year = 2005, } @article{CTT100394616, author = {Naotake Niwase and Junichi Yamagishi and Takao Kobayashi}, title = {Human walking motion synthesis with desired pace and stride length based on HSMM}, journal = {IEICE Trans. Information and Systems}, year = 2005, } @article{CTT100394620, author = {Makoto Tachibana and Junichi Yamagishi and Takashi Masuko and Takao Kobayashi}, title = {Speech synthesis with various emotional expressions and speaking styles by style interpolation and morphing}, journal = {IEICE Trans. Information and Systems}, year = 2005, } @article{CTT100394631, author = {Vladimir Braquet and Takao Kobayashi}, title = {A Wavelet based noise reduction algorithm for speech signal corrupted by coloured noise}, journal = {Proc. 9th European Conference on Speech Communication and Technology}, year = 2005, } @article{CTT100394633, author = {Makoto Tachibana and Junich Yamagishi and Takashi Masuko and Takao Kobayashi}, title = {Performance evaluation of style adaptation for hidden semi-Markov model based speech synthesis}, journal = {Proc. 9th European Conference on Speech Communication and Technology}, year = 2005, } @article{CTT100394632, author = {Juri Isogai and Junichi Yamagishi and Takao Kobayashi}, title = {Model adaptation and adaptive training using ESAT algorithm for HMM-based speech synthesis}, journal = {Proc. 9th European Conference on Speech Communication and Technology}, year = 2005, } @article{CTT100540822, author = {Junichi Yamagishi and Koji Onishi and Takashi Masuko and Takao Kobayashi}, title = {Acoustic modeling of speaking styles and emotional expressions in HMM-based speech synthesis}, journal = {IEICE Trans. Information and Systems}, year = 2005, } @article{CTT100394635, author = {Junichi Yamagishi and Takao Kobayashi}, title = {Adaptive training for hidden semi-Markov model}, journal = {Proc. 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2005, } @article{CTT100394636, author = {Dhany Arifianto and Takao Kobayashi}, title = {Voiced/Unvoiced determination of speech signal in noisy environment using harmonicity measure based on instantaneous frequency}, journal = {Proc. 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2005, } @article{CTT100502349, author = {Dhany Arifianto and Tomohiro Tanaka and Takashi Masuko and Takao Kobayashi}, title = {Robust F0 estimation of speech signal using harmonicity measure based on instantaneous frequency}, journal = {IEICE Trans. Information and Systems}, year = 2004, } @article{CTT100502346, author = {吉村貴克 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMMに基づくテキスト音声合成への混合励振源モデルとポストフィルタの導入}, journal = {電子情報通信学会論文誌}, year = 2004, } @article{CTT100502309, author = {橘 誠 and 山岸順一 and 益子貴史 and 小林隆夫}, title = {隠れセミマルコフモデルに基づく音声合成におけるスタイル適応の評価}, journal = {日本音響学会2004年秋季研究発表会講演論文集}, year = 2004, } @article{CTT100502307, author = {山岸順一 and 益子貴史 and 小林隆夫}, title = {HMM音声合成における対数正規分布による状態継続長のモデル化の検討}, journal = {日本音響学会2004年春季研究発表会講演論文集}, year = 2004, } @article{CTT100502320, author = {Takahiro Hoshiya and Heiga Zen and Shinji Sako and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {An HMM-based approach to speaker-dependent 100 bit/s speech coding}, journal = {Special Workshop in MAUI (SWIM), Lectures by Masters in Speech Processing, Conference CD-ROM}, year = 2004, } @article{CTT100502323, author = {Junichi Yamagishi and Takashi Masuko and Takao Kobayashi}, title = {HMM-based expressive speech synthesis - Towards TTS with arbitrary speaking styles and emotions}, journal = {Special Workshop in MAUI (SWIM), Lectures by Masters in Speech Processing, Conference CD-ROM}, year = 2004, } @article{CTT100502324, author = {Makoto Tachibana and Junichi Yamagishi and Takashi Masuko and Takao Kobayashi}, title = {HMM-based speech synthesis with various speaking styles using model interpolation}, journal = {Proc. the 2nd International Conference on Speech Prosody}, year = 2004, } @article{CTT100502325, author = {Masatsugu Okazaki and Toshifumi Kunimoto and Takao Kobayashi}, title = {A noise reduction technique for audio signals using Multi stage spectral subtraction}, journal = {Proc. the 18th International Congress on Acoustics}, year = 2004, } @article{CTT100502327, author = {Masatsugu Okazaki and Toshifumi Kunimoto and Takao Kobayashi}, title = {Multi-stage spectral subtraction for enhancement of audio signals}, journal = {Proc. the 2004 IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 2004, } @article{CTT100502334, author = {Keisuke Miyanaga and Takashi Masuko and Takao Kobayashi}, title = {A style control technique for HMM-based speech synthesis}, journal = {Proc. the 8th International Conference on Spoken Language Processing, CD-ROM}, year = 2004, } @article{CTT100502335, author = {Heiga Zen and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {Hidden semi-Markov model based speech synthesis}, journal = {Proc. the 8th International Conference on Spoken Language Processing, CD-ROM}, year = 2004, } @article{CTT100502336, author = {Junichi Yamagishi and Takashi Masuko and Takao Kobayashi}, title = {MLLR adaptation for hidden semi-Markov model based speech synthesis}, journal = {Proc. the 8th International Conference on Spoken Language Processing, CD-ROM}, year = 2004, } @article{CTT100502318, author = {山岸順一 and 橘 誠 and 益子貴史 and 小林隆夫}, title = {隠れセミマルコフモデルに基づく音声合成システムにおける最尤線形回帰によるスタイル適応の検討}, journal = {電子情報通信学会技術研究報告}, year = 2004, } @article{CTT100502316, author = {宮永圭介 and 益子貴史 and 小林隆夫}, title = {HMM音声合成における多様なスタイル実現のための制御法}, journal = {電子情報通信学会技術研究報告}, year = 2004, } @article{CTT100502314, author = {尾関 創 and 益子貴史 and 小林隆夫}, title = {多空間確率分布に基づくポーズのモデル化}, journal = {電子情報通信学会技術研究報告}, year = 2004, } @article{CTT100501472, author = {西本卓也 and 荒木雅弘 and 伊藤克亘 and 宇津呂武仁 and 甲斐充彦 and 河口信夫 and 河原達也 and 桂田浩一 and 小林隆夫 and 嵯峨山茂樹 and 下平博 and 伝康晴 and 徳田恵一 and 中村哲 and 新田恒雄 and 坂野秀樹他}, title = {Galatea: 音声対話擬人化エージェント開発キット}, journal = {インタラクション2004論文集}, year = 2004, } @article{CTT100502303, author = {高御堂雄三 and 益子貴史 and 小林隆夫}, title = {ボールの位置と速度に応じた捕球動作の生成}, journal = {情報処理学会第66回(平成16年)全国大会講演論文集}, year = 2004, } @article{CTT100502304, author = {尾関 創 and 益子貴史 and 小林隆夫}, title = {多空間確率分布によるポーズの位置と長さの同時モデル化}, journal = {日本音響学会2004年春季研究発表会講演論文集}, year = 2004, } @article{CTT100502305, author = {参納大樹 and 山岸順一 and 益子貴史 and 小林隆夫}, title = {HMM音声合成における構造的MAPLRによる発話スタイルの多様化の検討}, journal = {日本音響学会2004年春季研究発表会講演論文集}, year = 2004, } @article{CTT100502306, author = {橘 誠 and 山岸順一 and 益子貴史 and 小林隆夫}, title = {コンテキストクラスタリング決定木を用いた発話スタイル適応の評価}, journal = {日本音響学会2004年春季研究発表会講演論文集}, year = 2004, } @article{CTT100502308, author = {全 炳河 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMM音声合成のための継続長分布付き再推定}, journal = {日本音響学会2004年春季研究発表会講演論文集}, year = 2004, } @article{CTT100539609, author = {Junichi Yamagishi and Makoto Tachibana and Takashi Masuko and Takao Kobayashi}, title = {Speaking style adaptation using context clustering decision tree for HMM-based speech synthesis}, journal = {Proc. the 2004 IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 2004, } @article{CTT100538955, author = {Junichi Yamagishi and Masatsune Tamura and Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {A training method of average voice model for HMM-based speech synthesis}, journal = {IEICE Trans. Fundamentals of Electronics, Communications and Computer Sciences}, year = 2003, } @article{CTT100493112, author = {吉岡元貴 and 益子貴史 and 小林隆夫}, title = {隠れマルコフモデルに基づく腕の動きの生成}, journal = {情報処理学会第65回(平成15年)全国大会講演論文集}, year = 2003, } @article{CTT100488317, author = {Junichi Yamagishi and Masatsune Tamura and Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {A context clustering technique for average voice models}, journal = {IEICE Trans. Information and Systems}, year = 2003, } @article{CTT100492961, author = {Toru Takahashi and Keiichi Tokuda and Takao Kobayashi and Tadashi Kitamura}, title = {Mixture density models based on mel-cepstral representation of Gaussian Process}, journal = {IEICE Trans. Fundamentals of Electronics, Communications and Computer Sciences}, year = 2003, } @article{CTT100492963, author = {南角吉彦 and 徳田恵一 and 北村 正 and 小林隆夫}, title = {隠れマルコフモデルを用いた視覚音声認識のための正規化学習}, journal = {電子情報通信学会論文誌}, year = 2003, } @article{CTT100492966, author = {Junichi Yamagishi and Koji Onishi and Takashi Masuko and Takao Kobayashi}, title = {Modeling of various speaking styles and emotions for HMM-based speech synthesis}, journal = {Proc. the 8th Eurpean Conference on Speech Communication and Technology}, year = 2003, } @article{CTT100492970, author = {Dhany Arifianto and Takao Kobayashi}, title = {Performance evaluation of IFAS-based fundamental frequency estimator in noisy environments}, journal = {Proc. the 8th Eurpean Conference on Speech Communication and Technology}, year = 2003, } @article{CTT100492982, author = {Junichi Yamagishi and Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {A training method for average voice model based on shared decision tree context clustering and speaker adaptive training}, journal = {Proc. the 2003 IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 2003, } @article{CTT100492983, author = {Takahiro Hoshiya and Shinji Sako and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi}, title = {Improving the performance of HMM-based very low bitrate speech coding}, journal = {Proc. the 2003 IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 2003, } @article{CTT100492985, author = {Dhany Arifianto and Takao Kobayashi}, title = {IFAS-based Voiced/Unvoiced Classification of Speech Signal}, journal = {Proc. the 2003 IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 2003, } @article{CTT100492986, author = {岡崎雅嗣 and 岡村和久 and 小林隆夫}, title = {電子楽器用波形符号化方式の検討}, journal = {電子情報通信学会技術研究報告}, year = 2003, } @article{CTT100492987, author = {大西浩二 and 益子貴史 and 小林隆夫}, title = {HMM音声合成における異なる発話スタイル生成の検討}, journal = {電子情報通信学会技術研究報告}, year = 2003, } @article{CTT100492988, author = {嵯峨山茂樹 and 川本真一 and 下平博 and 新田恒雄 and 西本卓也 and 中村哲 and 伊藤克亘 and 森島繁生 and 四倉達夫 and 甲斐充彦 and 李晃伸 and 山下洋一 and 小林隆夫 and 徳田恵一 and 広瀬啓吉 and 峯松信明他}, title = {擬人化音声対話エージェントツールキット Galatea}, journal = {情報処理学会研究報告}, year = 2003, } @article{CTT100492991, author = {広畑 誠 and 益子貴史 and 小林隆夫}, title = {声道長正規化を用いた平均声モデル学習の検討}, journal = {電子情報通信学会技術研究報告}, year = 2003, } @article{CTT100492992, author = {山岸順一 and 益子貴史 and 徳田恵一 and 小林隆夫}, title = {HMM音声合成におけるコンテキストクラスタリング決定木を用いた話者適応の検討}, journal = {電子情報通信学会技術研究報告}, year = 2003, } @article{CTT100492993, author = {橘 誠 and 山岸順一 and 大西浩二 and 益子貴史 and 小林隆夫}, title = {HMM音声合成におけるモデル補間・適応による発話スタイルの多様化の検討}, journal = {電子情報通信学会技術研究報告}, year = 2003, } @article{CTT100492994, author = {岡崎雅嗣 and 国本利文 and 小林隆夫}, title = {信号の非定常性を考慮したスペクトルサブトラクション法}, journal = {電子情報通信学会技術研究報告}, year = 2003, } @article{CTT100492995, author = {大西浩二 and 益子貴史 and 小林隆夫}, title = {HMM音声合成における発話スタイルのモデル化と生成}, journal = {日本音響学会2003年春季研究発表会講演論文集}, year = 2003, } @article{CTT100493091, author = {岸本由加 and 全 炳河 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMM音声合成のためのポストフィルタ係数の自動決定}, journal = {日本音響学会2003年春季研究発表会講演論文集}, year = 2003, } @article{CTT100493093, author = {都築亮介 and 全 炳河 and 徳田恵一 and 北村 正 and 益子貴史 and 小林隆夫}, title = {HMM音声合成における感情表現のモデル化に関する検討}, journal = {日本音響学会2003年春季研究発表会講演論文集}, year = 2003, } @article{CTT100493096, author = {山岸順一 and 大西浩二 and 益子貴史 and 小林隆夫}, title = {多様な声質・発話スタイルによる音声合成のための適応手法の検討}, journal = {日本音響学会2003年春季研究発表会講演論文集}, year = 2003, } @article{CTT100493099, author = {星屋剛宏 and 酒向慎司 and 全 炳河 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {極低ビットレート音声符号化システムにおける決定木を用いたコードブックの自動決定}, journal = {日本音響学会2003年春季研究発表会講演論文集}, year = 2003, } @article{CTT100493106, author = {Dhany Arifianto and Takao Kobayashi}, title = {Voiced/Unvoiced decision using harmonicity measure}, journal = {Proc. the 2003 Spring Meeting of the Acoustical Society of Japan}, year = 2003, } @article{CTT100493109, author = {今井田誠治 and 益子貴史 and 小林隆夫}, title = {音声と音楽およびその混合音のインデキシング}, journal = {日本音響学会2003年春季研究発表会講演論文集}, year = 2003, } @article{CTT100493114, author = {高御堂雄三 and 羽岡哲郎 and 益子貴史 and 小林隆夫}, title = {隠れマルコフモデルに基づくハンドジェスチャー生成の検討}, journal = {情報処理学会第65回(平成15年)全国大会講演論文集}, year = 2003, } @article{CTT100493117, author = {山岸順一 and 大西浩二 and 益子貴史 and 小林隆夫}, title = {HMM音声合成における発話スタイルの制御}, journal = {情報処理学会第65回(平成15年)全国大会講演論文集}, year = 2003, } @article{CTT100493118, author = {益子貴史 and 徳田恵一 and 小林隆夫}, title = {HMMからの尤度最大基準に基づく条件つきパラメータ生成の検討}, journal = {日本音響学会2003年秋季研究発表会講演論文集}, year = 2003, } @article{CTT100493122, author = {山岸順一 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {コンテキストクラスタリング決定木を用いた話者適応の検討}, journal = {日本音響学会2003年秋季研究発表会講演論文集}, year = 2003, } @article{CTT100493123, author = {橘 誠 and 山岸順一 and 益子貴史 and 小林隆夫}, title = {HMM音声合成における異なる発話スタイルへの適応の検討}, journal = {日本音響学会2003年秋季研究発表会講演論文集}, year = 2003, } @article{CTT100493128, author = {Takao Kobayashi and Junichi Yamagishi and Takashi Masuko}, title = {Average voice model for synthesizing speech with arbitrary speaker's voice}, journal = {Proc. 2002 2nd Plenary Meeting and Symposium on Prosody and Speech Processing}, year = 2003, } @article{CTT100501471, author = {嵯峨山茂樹 and 伊藤克亘 and 宇津呂武仁 and 甲斐充彦 and 小林隆夫 and 下平博 and 伝康晴 and 徳田恵一 and 中村哲 and 西本卓也 and 新田恒雄 and 広瀬啓吉 and 峯松信明 and 森島繁生 and 山下洋一 and 山田篤他}, title = {擬人化音声対話エージェント基本ソフトウェアの開発プロジェクト報告}, journal = {情報処理学会研究報告}, year = 2003, } @article{CTT100468800, author = {田村正統 and 益子貴史 and 徳田恵一 and 小林隆夫}, title = {HMMに基づく音声合成におけるピッチ・スペクトルの話者適応}, journal = {電子情報通信学会誌}, year = 2002, } @article{CTT100468801, author = {Tomohiro Tanaka and Takao Kobayashi and Dhany Arifianto and Takashi Masuko}, title = {Fundamental frequency estimation based on instantaneous frequency amplitude spectrum}, journal = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 2002, } @article{CTT100476774, author = {高御堂雄三 and 徳田恵一 and 北村 正 and 益子貴史 and 小林隆夫}, title = {HMMを用いた音声合成における学習データ量と音質の調査}, journal = {日本音響学会2002年春季研究発表会講演論文集}, year = 2002, } @article{CTT100476775, author = {高橋 徹 and 徳田恵一 and 小林隆夫 and 北村 正}, title = {動的特徴量を考慮した統計的尺度に基づくメルケプストラム係数のベクトル量子化}, journal = {日本音響学会2002年春季研究発表会講演論文集}, year = 2002, } @article{CTT100476776, author = {三浦和人 and 小林隆夫 and 竹林洋一}, title = {ウェアラブルコンピュータとコンパニオンロボットによるBluetoothを利用した動画像通信とインタラクション }, journal = {情報処理学会第64回(平成14年)全国大会講演論文集}, year = 2002, } @article{CTT100476974, author = {星屋剛宏 and 酒向慎司 and 全 炳河 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMMに基づいた極低ビットレート音声符号化システムの性能改善}, journal = {日本音響学会2002年秋季研究発表会講演論文集}, year = 2002, } @article{CTT100476975, author = {岸本由加 and 全 炳河 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMM音声合成のためのポストフィルタリング}, journal = {日本音響学会2002年秋季研究発表会講演論文集}, year = 2002, } @article{CTT100476976, author = {山岸順一 and 田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {話者適応のための平均声モデル学習法の検討}, journal = {日本音響学会2002年秋季研究発表会講演論文集}, year = 2002, } @article{CTT100476977, author = {山岸順一 and 田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {話者適応のための平均声モデル学習法の評価}, journal = {日本音響学会2002年秋季研究発表会講演論文集}, year = 2002, } @article{CTT100476978, author = {七里建吾 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {固有声を用いたHMM音声合成における声質評価}, journal = {日本音響学会2002年秋季研究発表会講演論文集}, year = 2002, } @article{CTT100476979, author = {嵯峨山茂樹 and 伊藤克亘 and 宇津呂武仁 and 甲斐充彦 and 小林隆夫 and 下平博 and 伝康晴 and 徳田恵一 and 中村哲 and 西本卓也 and 新田恒雄 and 広瀬啓吉 and 森島繁生 and 峯松信明 and 山下洋一 and 山田篤 and 李晃伸}, title = {擬人化音声対話エージェント開発プロジェクト (招待講演)}, journal = {日本音響学会2002年春季研究発表会講演論文集}, year = 2002, } @article{CTT100476980, author = {山下洋一 and 峯松信明 and 徳田恵一 and 小林隆夫 and 広瀬啓吉}, title = {擬人化音声対話エージェントにおける音声合成}, journal = {日本音響学会2002年春季研究発表会講演論文集}, year = 2002, } @article{CTT100476981, author = {山岸順一 and 田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {HMM音声合成におけるコンテキストクラスタリング決定木の構築法の検討}, journal = {日本音響学会2002年春季研究発表会講演論文集}, year = 2002, } @article{CTT100476982, author = {全 炳河 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {部分的共有を行ったHMMからの音声合成}, journal = {日本音響学会2002年春季研究発表会講演論文集}, year = 2002, } @article{CTT100476983, author = {田村正統 and 益子貴史 and 徳田恵一 and 小林隆夫}, title = {HMM音声合成におけるSATを用いた平均声モデルの学習}, journal = {日本音響学会2002年春季研究発表会講演論文集}, year = 2002, } @article{CTT100477621, author = {Keiichi Tokuda and Takashi Mausko and Noboru Miyazaki and Takao Kobayashi}, title = {Multi-space probability distribution HMM (Invited paper)}, journal = {IEICE Trans. Information and Systems}, year = 2002, } @article{CTT100477625, author = {川本真一 and 下平博 and 新田恒雄 and 西本卓也 and 中村哲 and 伊藤克亘 and 森島繁生 and 四倉達夫 and 甲斐充彦 and 李晃伸 and 山下洋一 and 小林隆夫 and 徳田恵一 and 広瀬啓吉 and 峯松信明 and 山田篤 and 伝康晴 and 宇津呂武仁 and 他}, title = {カスタマイズ性を考慮した擬人化音声対話ソフトウェアツールキットの設計}, journal = {情報処理学会論文誌}, year = 2002, } @article{CTT100477628, author = {酒向慎司 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMMに基づいた視聴覚テキスト音声合成 － 画像ベースアプローチ}, journal = {情報処理学会論文誌}, year = 2002, } @article{CTT100477630, author = {佐藤隆之 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {話者照合におけるHMM音声合成による合成音声の判別}, journal = {情報処理学会論文誌}, year = 2002, } @article{CTT100477646, author = {高橋 徹 and 徳田恵一 and 小林隆夫 and 北村 正}, title = {スペクトル分析のための尺度を用いたメルケプストラム係数のベクトル量子化}, journal = {電子情報通信学会論文誌}, year = 2002, } @article{CTT100477648, author = {益子 貴史 and 徳田 恵一 and 小林 隆夫}, title = {HMMに基づいた極低ビットレート音声符号化における不特定話者への対応}, journal = {電子情報通信学会論文誌}, year = 2002, } @article{CTT100477650, author = {S. Kawamoto and H. Shimodaira and T. Nitta and T. Nishimoto and S. Nakamura and K. Itou and S. Morishima and T. Yotsukura and A. Kai and A. Lee and Y. Yamashita and T. Kobayashi and et al.}, title = {Open-source software for developing anthropomorphic spoken dialog agents}, journal = {Proc. International Workshop on Lifelike Animated Agents, Tools, Affective Functions, and Applications}, year = 2002, } @article{CTT100477651, author = {Kengo Shichiri and Atsushi Sawabe and Takayoshi Yoshimura and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {Eigenvoices for HMM-based speech synthesis}, journal = {Proc. 7th International Conference on Spoken Language Processing}, year = 2002, } @article{CTT100477653, author = {Junichi Yamagishi and Masatsune Tamura and Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {A context clustering technique for average voice model in HMM-based speech synthesis}, journal = {Proc. 7th International Conference on Spoken Language Processing}, year = 2002, } @article{CTT100477654, author = {Takao Kobayashi and Masatsune Tamura and Takashi Masuko}, title = {Speech synthesis with arbitrary speaker's voice from average voice - Speaker adaptation of F0 and spectrum for HMM-based speech synthesis}, journal = {Proc. Symposium on Prosody and Speech Processing}, year = 2002, } @article{CTT100477655, author = {山岸順一 and 田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {平均声モデル構築におけるコンテキストクラスタリングと話者適応学習の検討}, journal = {電子情報通信学会技術研究報告}, year = 2002, } @article{CTT100477657, author = {山岸順一 and 田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {平均声モデル構築のためのコンテキストクラスタリング手法の検討}, journal = {電子情報通信学会技術研究報告}, year = 2002, } @article{CTT100477658, author = {山下洋一 and 喜多竜二 and 峯松信明 and 吉村貴克 and 徳田恵一 and 田村正統 and 益子貴史 and 小林隆夫 and 広瀬啓吉}, title = {マルチモーダルコミュニケーションのための音声合成プラットホーム}, journal = {情報処理学会研究報告}, year = 2002, } @article{CTT100480458, author = {羽岡哲郎 and 益子貴史 and 小林隆夫}, title = {隠れマルコ不モデルに基づくハンドジェスチャーアニメーション生成}, journal = {電子情報通信学会技術研究報告}, year = 2002, } @article{CTT100477659, author = {川本真一 and 下平博 and 新田恒雄 and 西本卓也 and 中村哲 and 伊藤克亘 and 森島繁生 and 四倉達夫 and 甲斐充彦 and 李晃伸 and 山下洋一 and 小林隆夫 and 徳田恵一 and 広瀬啓吉 and 峯松信明 and 山田篤 and 伝康晴 and 宇津呂武仁 and 他}, title = {擬人化音声対話エージェントツールキットの基本設計}, journal = {情報処理学会研究報告}, year = 2002, } @article{CTT100460603, author = {佐藤隆之 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {合成音声に対する安全性を考慮したテキスト指定型話者照合システムの検討}, journal = {日本音響学会2001年春季研究発表会講演論文集}, year = 2001, } @article{CTT100456904, author = {Kazuhito Koishida and Keiichi Tokuda and Takashi Mausko and Takao Kobayashi}, title = {Vector quantization of speech spectral parameters using statistics of static and dynamic features}, journal = {IEICE Trans. Information and Systems}, year = 2001, } @article{CTT100456910, author = {Masatsune Tamura and Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {Adaptation of pitch and spectrum for HMM-Based speech synthesis using MLLR}, journal = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 2001, } @article{CTT100460320, author = {川本真一 and 下平 博 and 嵯峨山茂樹 and 新田恒雄 and 西本卓也 and 中村 哲 and 伊藤克亘 and 森島繁生 and 四倉達夫 and 甲斐充彦 and 李 晃伸 and 山下洋一 and 小林隆夫 and 徳田恵一 and 広瀬啓吉 and 峯松信明 }, title = {インタラクティブ性を重視した擬人化音声対話エージェントの基本設計}, journal = {人工知能学会研究会資料}, year = 2001, } @article{CTT100460321, author = {篠澤康彦 and 安倍 健 and 小林隆夫 and 市村 岳}, title = {渦流探傷センサによる銅配管腐食評価手法の検討}, journal = {日本非破壊検査協会平成13年度春季講演会論文集}, year = 2001, } @article{CTT100460407, author = {Masatsune Tamura and Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {Text-to-speech synthesis with arbitrary speaker's voice from average voice}, journal = {Proc. 7th European Conference on Speech Communication and Technology}, year = 2001, } @article{CTT100460408, author = {Chiyomi Miyajima and Yousuke Hattori and Keiichi Tokuda and Takashi Mausko and Takao Kobayashi and Tadashi Kitamura}, title = {Text-independent speaker identification using Gaussian mixture models based on multi-space probability distribution}, journal = {IEICE Trans. Information and Systems}, year = 2001, } @article{CTT100460425, author = {Takayuki Satoh and Takashi Masuko and Takao Kobayashi and Keiichi Tokuda}, title = {A robust speaker verification system against imposture using an HMM-based speech synthesis}, journal = {Proc. 7th European Conference on Speech Communication and Technology}, year = 2001, } @article{CTT100460426, author = {Takayoshi Yoshimura and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {Mixed excitation for HMM-based speech synthesis}, journal = {Proc. 7th European Conference on Speech Communication and Technology}, year = 2001, } @article{CTT100460427, author = {Chiyomi Miyajima and Yousuke Hattori and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {Speaker identification using Gaussian mixture models based on multi-space probability distribution}, journal = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 2001, } @article{CTT100460479, author = {佐藤隆之 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {合成音声に対する安全性を考慮したテキスト指定型話者照合システムの検討}, journal = {電子情報通信学会技術研究報告}, year = 2001, } @article{CTT100460480, author = {吉岡元貴 and 田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {HMM音声合成における韻律の変動要因用の検討}, journal = {電子情報通信学会技術研究報告}, year = 2001, } @article{CTT100460481, author = {石松喜伸 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMM音声合成におけるガンマ分布状態継続長モデルの検討}, journal = {電子情報通信学会技術研究報告}, year = 2001, } @article{CTT100460482, author = {吉村貴克 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMMに基づく音声合成への混合励振源モデルとポストフィルタの導入}, journal = {電子情報通信学会技術研究報告}, year = 2001, } @article{CTT100460483, author = {全 炳河 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {有声／無声境界の動的特徴量を考慮したピッチのモデル化}, journal = {電子情報通信学会技術研究報告}, year = 2001, } @article{CTT100460484, author = {沢部 敦 and 七里建吾 and 吉村貴克 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMM音声合成おけるスペクトル・ピッチへの固有声手法の適用}, journal = {電子情報通信学会技術研究報告}, year = 2001, } @article{CTT100460485, author = {益子貴史 and 小林隆夫 and 徳田恵一}, title = {不特定話者対応HMM認識ボコーダの検討}, journal = {電子情報通信学会技術研究報告}, year = 2001, } @article{CTT100460486, author = {田村正統 and 益子貴史 and 徳田恵一 and 小林隆夫}, title = {HMM音声合成におけるMLLRを用いたピッチ・スペクトルの話者適応}, journal = {電子情報通信学会技術研究報告}, year = 2001, } @article{CTT100460487, author = {田中智宏 and 益子貴史 and 小林隆夫}, title = {瞬時周波数振幅スペクトルに基づくピッチ抽出法の検討}, journal = {電子情報通信学会技術研究報告}, year = 2001, } @article{CTT100460488, author = {熊倉俊之 and 田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {HMM音声合成システムのためのテキスト処理部の構築}, journal = {日本音響学会2001年春季研究発表会講演論文集}, year = 2001, } @article{CTT100460597, author = {沢部 敦 and 七里建吾 and 吉村貴克 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {固有声に基づいたtriphoneによる音声合成}, journal = {日本音響学会2001年春季研究発表会講演論文集}, year = 2001, } @article{CTT100460598, author = {吉村貴克 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMMに基づく音声合成のための励振源モデルの検討}, journal = {日本音響学会2001年春季研究発表会講演論文集}, year = 2001, } @article{CTT100460599, author = {廣谷定男 and 益子貴史 and 小林隆夫}, title = {混合励振源を用いた低ビットレート音声符号化の品質向上の検討}, journal = {日本音響学会2001年春季研究発表会講演論文集}, year = 2001, } @article{CTT100460600, author = {田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {HMMに基づく音声合成システムにおけるピッチ・スペクトルの話者適応}, journal = {日本音響学会2001年春季研究発表会講演論文集}, year = 2001, } @article{CTT100460601, author = {酒向慎司 and 近藤重一 and 益子貴史 and 徳田恵一 and 小林隆夫 and 北村 正}, title = {唇動画像と音声によるマルチモーダルデータベースの構築}, journal = {日本音響学会2001年春季研究発表会講演論文集}, year = 2001, } @article{CTT100460621, author = {小林隆夫}, title = {ソース・フィルタ理論}, journal = {日本音響学会誌}, year = 2001, } @article{CTT100460620, author = {高橋 徹 and 徳田恵一 and 小林隆夫 and 北村 正}, title = {スペクトル分析のための基準を用いたHMMの学習アルゴリズム}, journal = {日本音響学会2001年秋季研究発表会講演論文集}, year = 2001, } @article{CTT100460619, author = {全 炳河 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {動的特徴量を考慮したピッチの高精度モデル化手法}, journal = {日本音響学会2001年秋季研究発表会講演論文集}, year = 2001, } @article{CTT100460618, author = {石松喜伸 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMM音声合成のためのガンマ分布を用いた状態継続長のモデル化}, journal = {日本音響学会2001年秋季研究発表会講演論文集}, year = 2001, } @article{CTT100460617, author = {吉岡元貴 and 田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {HMM音声合成に用いるコンテキストの検討}, journal = {日本音響学会2001年秋季研究発表会講演論文集}, year = 2001, } @article{CTT100460616, author = {沢部 敦 and 七里建吾 and 吉村貴克 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {固有声に基づいた音声合成おけるピッチのモデル化}, journal = {日本音響学会2001年秋季研究発表会講演論文集}, year = 2001, } @article{CTT100460615, author = {田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {HMMに基づく音声合成システムにおける音韻継続長の話者適応}, journal = {日本音響学会2001年秋季研究発表会講演論文集}, year = 2001, } @article{CTT100460614, author = {山岸順一 and 田村正統 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {MM音声合成における平均声モデルの学習セットの検討}, journal = {日本音響学会2001年秋季研究発表会講演論文集}, year = 2001, } @article{CTT100460613, author = {吉村貴克 and 徳田恵一 and 益子貴史 and 小林隆夫 and 北村 正}, title = {HMMに基づく音声合成における品質改善に関する検討}, journal = {日本音響学会2001年秋季研究発表会講演論文集}, year = 2001, } @article{CTT100460612, author = {堤 啓児 and 益子貴史 and 小林隆夫}, title = {バイモーダル音声データベースの構築}, journal = {日本音響学会2001年秋季研究発表会講演論文集}, year = 2001, } @article{CTT100460604, author = {日小田芳郎 and 益子貴史 and 小林隆夫 and 徳田恵一}, title = {不特定話者対応HMM認識ボコーダに関する検討}, journal = {電子情報通信学会2001年総合大会講演論文集}, year = 2001, } @article{CTT100460602, author = {高橋 徹 and 徳田恵一 and 小林隆夫 and 北村 正}, title = {音声のメルケプストラム表現に基づいたGMM}, journal = {日本音響学会2001年春季研究発表会講演論文集}, year = 2001, } @article{CTT100437506, author = {徳田 恵一 and 益子 貴史 and 宮崎 昇 and 小林 隆夫}, title = {多空間上の確率分布に基づいたHMM}, journal = {電子情報通信学会論文誌}, year = 2000, } @article{CTT100437505, author = {Takayoshi Yoshimura and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {Speaker Interpolation for HMM-based Speech Synthesis System}, journal = {J. Acoust. Soc. Jpn. (E)}, year = 2000, } @article{CTT100437504, author = {Kazuhito Koishida and Gou Hirabayashi and Keiichi Tokuda and Takao Kobayashi}, title = {A 16 kb/s Wideband CELP-Based Speech Coder Using Mel-Generalized Cepstral Analysis}, journal = {IEICE Trans. Information and Systems}, year = 2000, } @article{CTT100437507, author = {益子 貴史 and 徳田 恵一 and 宮崎 昇 and 小林 隆夫}, title = {多空間確率分布HMMによるピッチパターン生成}, journal = {電子情報通信学会論文誌}, year = 2000, } @article{CTT100437511, author = {Yoshihiko Nankaku and Keiichi Tokuda and Tadashi Kitamura and Takao Kobayashi}, title = {Normalized Training for HMM-Based Visual Speech Recognition}, journal = {Proc. IEEE International Conference on Image Processing}, year = 2000, } @article{CTT100437512, author = {Shinji Sako and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {HMM-Based Text-to-Audio-Visual Speech Synthesis}, journal = {Proc. 6th International Conference on Spoken Language Processing}, year = 2000, } @article{CTT100437513, author = {Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {Imposture Using Synthetic Speech against Speaker Verification Based on Spectrum and Pitch}, journal = {Proc. 6th International Conference on Spoken Language Processing}, year = 2000, } @article{CTT100437514, author = {Tohru Takahashi and Keiichi Tokuda and Takao Kobayashi and Tadashi Kitamura}, title = {Vector Quantization of Mel-cepstral Coefficients Based on a Statistical Measure}, journal = {Proc. 2000 IEEE International Symposium on Intelligent Signal Processing and Communication Systems}, year = 2000, } @article{CTT100437519, author = {高橋 徹 and 徳田 恵一 and 小林 隆夫 and 北村 正}, title = {スペクトル分析のための尺度を用いたメルケプストラム係数のベクトル量子化}, journal = {電子情報通信学会技術研究報告}, year = 2000, } @article{CTT100437520, author = {Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {Imposture Using Synthetic Speech against Text-Prompted Speaker Verification Based on Spectrum and Pitch}, journal = {電子情報通信学会技術研究報告}, year = 2000, } @article{CTT100437521, author = {廣谷定男 and 真下 哲 and 益子貴史 and 小林 隆夫}, title = {混合励振源を用いた極低ビットレート音声符号化の検討}, journal = {電子情報通信学会技術研究報告}, year = 2000, } @article{CTT100437543, author = {吉村 貴克 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {尤度最大化基準による HMM からの音声パラメータ生成法の評価}, journal = {日本音響学会2000年春季研究発表会講演論文集}, year = 2000, } @article{CTT100437544, author = {真下 哲 and 益子 貴史 and 小林 隆夫 and 徳田 恵一}, title = {1.6kbps 低ビットレート符号化方式の検討}, journal = {日本音響学会2000年春季研究発表会講演論文集}, year = 2000, } @article{CTT100437545, author = {服部 陽介 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {多空間ガウス混合モデルを用いた話者認識}, journal = {日本音響学会2000年春季研究発表会講演論文集}, year = 2000, } @article{CTT100437546, author = {益子 貴史 and 徳田 恵一 and 小林 隆夫}, title = {スペクトルとピッチに基づく話者照合に対する合成音声による詐称}, journal = {日本音響学会2000年春季研究発表会講演論文集}, year = 2000, } @article{CTT100437547, author = {田村 正統 and 益子 貴史 and 徳田 恵一 and 小林 隆夫}, title = {HMM に基づく音声合成システムのためのテキスト解析の検討}, journal = {日本音響学会2000年春季研究発表会講演論文集}, year = 2000, } @article{CTT100437548, author = {酒向 慎司 and 徳田恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {ピクセルベースアプローチによるHMMに基づいた唇動画像生成}, journal = {電子情報通信学会2000年総合大会講演論文集}, year = 2000, } @article{CTT100437549, author = {吉村 貴克 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づく音声合成システムの自動構築}, journal = {日本音響学会2000年秋季研究発表会講演論文集}, year = 2000, } @article{CTT100437550, author = {酒向 慎司 and 徳田恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づいた音声・唇動画像の同時生成 － 画像ベースアプローチ －}, journal = {日本音響学会2000年秋季研究発表会講演論文集}, year = 2000, } @article{CTT100437684, author = {石松 喜伸 and 徳田 恵一 and 北村 正 and 小林 隆夫}, title = {メル一般化ケプストラム分析に基づくMELP音声符号化}, journal = {電子情報通信学会2000年基礎・境界ソサイエティ大会講演論文集}, year = 2000, } @article{CTT100444526, author = {益子 貴史 and 田村 正統 and 徳田 恵一 and 小林 隆夫}, title = {HMMに基づく音声合成システムにおけるMAP-VFSを用いた声質変換}, journal = {電子情報通信学会論文誌}, year = 2000, } @article{CTT100437510, author = {Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {Speech Parameter Generation Algorithms for HMM-Based Speech Synthesis}, journal = {Proc. IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 2000, } @article{CTT100437509, author = {益子 貴史 and 徳田 恵一 and 小林 隆夫}, title = {話者照合システムに対する合成音声による詐称}, journal = {電子情報通信学会論文誌}, year = 2000, } @article{CTT100437508, author = {吉村 貴克 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づく音声合成におけるスペクトル・ピッチ・継続長の同時モデル化}, journal = {電子情報通信学会論文誌}, year = 2000, } @article{CTT100424651, author = {広井 順 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMM に基づいた極低ビットレート音声符号化}, journal = {電子情報通信学会論文誌}, year = 1999, } @article{CTT100424456, author = {高橋 史生 and 益子 貴史 and 徳田 恵一 and 小林 隆夫}, title = {不特定話者HMM認識ボコーダの音質向上に関する検討}, journal = {日本音響学会平成11年度春季研究発表会講演論文集}, year = 1999, } @article{CTT100431695, author = {一ツ松 孝文 and 益子 貴史 and 小林 隆夫 and 徳田 恵一}, title = {合成音声を用いたテキスト指定型話者照合システムにおける詐称の検討}, journal = {日本音響学会平成11年度春季研究発表会講演論文集}, year = 1999, } @article{CTT100430151, author = {若子 武士 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {対数スペクトルの任意基底関数による展開に基づく音声のスペクトル推定}, journal = {電子情報通信学会論文誌}, year = 1999, } @article{CTT100425249, author = {近藤 重一 and 益子 貴史 and 徳田 恵一 and 小林 隆夫}, title = {HMMに基づくテキストからのバイモーダル音声合成に関する検討}, journal = {日本音響学会平成11年度春季研究発表会講演論文集}, year = 1999, } @article{CTT100425248, author = {田村 正統 and 益子 貴史 and 徳田 恵一 and 小林 隆}, title = {MLLRおよびMAP/VFSを用いたHMM音声合成における話者適応}, journal = {日本音響学会平成11年度春季研究発表会講演論文集}, year = 1999, } @article{CTT100425247, author = {吉村 貴克 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づく音声合成のためのスペクトラム, ピッチ, 状態継続長のモデル化}, journal = {日本音響学会平成11年度春季研究発表会講演論文集}, year = 1999, } @article{CTT100425246, author = {柳ヶ瀬 滋夫 and 小石田 和人 and 徳田 恵一 and 小林 隆夫}, title = {広帯域音声のMGC-CELP符号化方式における演算量に関する検討}, journal = {日本音響学会平成11年度春季研究発表会講演論文集}, year = 1999, } @article{CTT100424455, author = {広井 順 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づいた唇動画像の生成 － 画像ベースアプローチ －}, journal = {日本音響学会平成11年度春季研究発表会講演論文集}, year = 1999, } @article{CTT100425245, author = {中西 貴裕 and 徳田 恵一 and 小林 隆夫 and 北村 正}, title = {MDL基準による音声分析フレーム長と分析次数の同時最適決定}, journal = {日本音響学会平成11年度春季研究発表会講演論文集}, year = 1999, } @article{CTT100425244, author = {南角 吉彦 and 徳田恵一 and 北村 正 and 小林 隆夫}, title = {視覚音声認識のための輝度および位置の正規化学習}, journal = {電子情報通信学会1999年総合大会講演論文集}, year = 1999, } @article{CTT100424666, author = {吉村 貴克 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づくピッチパターン生成における動的特徴量の効果}, journal = {日本音響学会平成11年度秋季研究発表会講演論文集}, year = 1999, } @article{CTT100424665, author = {徳田 恵一 and 益子 貴史 and 小林 隆夫}, title = {尤度最大化基準によるHMMからの音声パラメータ生成法の検討}, journal = {日本音響学会平成11年度秋季研究発表会講演論文集}, year = 1999, } @article{CTT100424664, author = {小山 晃俊 and 徳田 恵一 and 小林 隆夫 and 北村 正}, title = {固有声(eigenvoice)に基づいた音声合成}, journal = {日本音響学会平成11年度秋季研究発表会講演論文集}, year = 1999, } @article{CTT100424663, author = {小林隆夫}, title = {HMMに基づく音声合成(招待講演)}, journal = {日本音響学会平成11年度秋季研究発表会講演論文集}, year = 1999, } @article{CTT100424658, author = {南角 吉彦 and 徳田 恵一 and 北村 正 and 小林 隆夫}, title = {Normalized Training for HMM-Based Automatic Lipreading}, journal = {電子情報通信学会技術研究報告}, year = 1999, } @article{CTT100424657, author = {酒向慎司 and 徳田恵一 and 北村 正 and 益子貴史 and 小林隆夫}, title = {ピクセルベースアプローチによるHMMに基づいた唇動画像の生成}, journal = {電子情報通信学会技術研究報告}, year = 1999, } @article{CTT100424656, author = {吉村 貴克 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づく音声合成におけるスペクトル・ピッチ・状態継続長の同時モデル化}, journal = {電子情報通信学会技術研究報告}, year = 1999, } @article{CTT100424655, author = {Keiichi Tokuda and Takashi Masuko and Noboru Miyazaki and Takao Kobayashi}, title = {Hidden Markov Models Based on Multi-Space Probability Distribution for Pitch Pattern Modeling}, journal = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 1999, } @article{CTT100424654, author = {Takayoshi Yoshimura and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi and Tadashi Kitamura}, title = {Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis}, journal = {Proceedings of 6th European Conference on Speech Communication and Technology}, year = 1999, } @article{CTT100424653, author = {Takashi Masuko and Takafumi Hitotsumatsu and Keiichi Tokuda and Takao Kobayashi}, title = {On the Security of HMM-Based Speaker Verification Systems Against Imposture Using Synthetic Speech}, journal = {Proceedings of 6th European Conference on Speech Communication and Technology}, year = 1999, } @article{CTT100424652, author = {Masatsune Tamura and Shigekazu Kondo and Takashi Masuko and Takao Kobayashi}, title = {Text-to-Audio-Visual Speech Synthesis Based on Parameter Generation from HMM}, journal = {Proceedings of 6th European Conference on Speech Communication and Technology}, year = 1999, } @article{CTT100423268, author = {小石田 和人 and 徳田 恵一 and 小林 隆夫 and 今井 聖}, title = {メル一般化ケプストラム分析に基づくCELP音声符号化}, journal = {電子情報通信学会論文誌}, year = 1998, } @article{CTT100424020, author = {小林隆夫}, title = {音声分析の統一的手法}, journal = {Journal of Signal Processing「信号処理」}, year = 1998, } @article{CTT100423987, author = {山内 和幸 and 益子 貴史 and 小林 隆夫}, title = {メルケプストラムをパラメータとする音声強調における事前情報の検討}, journal = {日本音響学会平成10年度春季研究発表会講演論文集}, year = 1998, } @article{CTT100423986, author = {若子武士 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {2次オールパス関数による周波数変換を利用したメルケプストラム分析の音声分析合成における評価}, journal = {日本音響学会平成10年度春季研究発表会講演論文集}, year = 1998, } @article{CTT100423985, author = {徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {2次オールパス関数による周波数変換を利用した音声のメルケプストラム分析}, journal = {日本音響学会平成10年度春季研究発表会講演論文集}, year = 1998, } @article{CTT100423984, author = {田村 正統 and 益子 貴史 and 徳田 恵一 and 小林 隆夫}, title = {HMM音声合成に基づく声質変換における話者適応手法の検討}, journal = {日本音響学会平成10年度春季研究発表会講演論文集}, year = 1998, } @article{CTT100423983, author = {増渕 淳 and 田村 正統 and 宮川 公成 and 益子 貴史 and 小林 隆夫 and 徳田 恵一}, title = {HMMに基づくテキストからの音声・唇動画像の同時生成}, journal = {日本音響学会平成10年度春季研究発表会講演論文集}, year = 1998, } @article{CTT100423982, author = {平林 剛 and 小石田 和人 and 徳田 恵一 and 小林 隆夫}, title = {メル一般化ケプストラム分析に基づく広帯域CELPの品質評価}, journal = {日本音響学会平成10年度春季研究発表会講演論文集}, year = 1998, } @article{CTT100423981, author = {加藤 寿彦 and 益子 貴史 and 小林 隆夫 and 徳田 恵一}, title = {多空間出力分布並列HMMによるピッチパタン生成}, journal = {日本音響学会平成10年度春季研究発表会講演論文集}, year = 1998, } @article{CTT100423980, author = {宮崎 昇 and 徳田 恵一 and 益子 貴史 and 小林 隆夫}, title = {多空間上の確率分布に基づいたHMMによるピッチパタン生成}, journal = {日本音響学会平成10年度春季研究発表会講演論文集}, year = 1998, } @article{CTT100423979, author = {宮崎 昇 and 徳田 恵一 and 益子 貴史 and 小林 隆夫}, title = {ピッチパタンモデリングのための多空間上の確率分布に基づいたHMM}, journal = {日本音響学会平成10年度春季研究発表会講演論文集}, year = 1998, } @article{CTT100423976, author = {益子 貴史 and 徳田 恵一 and 小林 隆夫}, title = {HMM認識ボコーダの不特定話者化に関する検討}, journal = {日本音響学会平成10年度秋季研究発表会講演論文集}, year = 1998, } @article{CTT100423975, author = {田村 正統 and 益子 貴史 and 小林 隆夫 and 徳田 恵一}, title = {音声駆動およびテキスト・音声駆動による唇動画像の生成}, journal = {日本音響学会平成10年度秋季研究発表会講演論文集}, year = 1998, } @article{CTT100423974, author = {吉村 貴克 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づく音声合成のための状態継続長モデルの構築}, journal = {日本音響学会平成10年度秋季研究発表会講演論文集}, year = 1998, } @article{CTT100423973, author = {若子 武士 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {2次オールパス関数による周波数変換を利用したメルケプストラム分析の音声認識における評価}, journal = {日本音響学会平成10年度秋季研究発表会講演論文集}, year = 1998, } @article{CTT100423295, author = {宮崎 昇 and 徳田 恵一 and 益子 貴史 and 小林 隆夫}, title = {多空間上の確率分布を用いた HMM によるピッチパタン生成の検討}, journal = {電子情報通信学会技術研究報告}, year = 1998, } @article{CTT100423294, author = {宮崎 昇 and 徳田 恵一 and 益子 貴史 and 小林 隆夫}, title = {多空間上の確率分布に基づいたHMMとピッチパタンモデリングへの応用}, journal = {電子情報通信学会技術研究報告}, year = 1998, } @article{CTT100423293, author = {田村 正統 and 益子 貴史 and 小林 隆夫}, title = {テキスト及び音声からの唇動画像の自動生成}, journal = {Human Interface News and Report}, year = 1998, } @article{CTT100423292, author = {吉村 貴克 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づく音声合成のための状態継続長モデルの構築}, journal = {電子情報通信学会技術研究報告}, year = 1998, } @article{CTT100423291, author = {広井 順 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {HMMに基づいた極低ビットレート音声符号化}, journal = {電子情報通信学会技術研究報告}, year = 1998, } @article{CTT100423290, author = {若子 武士 and 徳田 恵一 and 益子 貴史 and 小林 隆夫 and 北村 正}, title = {対数スペクトルの任意基底関数による展開に基づいた音声のスペクトル推定とその応用}, journal = {電子情報通信学会技術研究報告}, year = 1998, } @article{CTT100423289, author = {小林隆夫}, title = {音声のケプストラム分析，メルケプストラム分析}, journal = {電子情報通信学会技術研究報告}, year = 1998, } @article{CTT100423288, author = {一ツ松 孝文 and 益子 貴史 and 小林 隆夫 and 徳田 恵一}, title = {HMMに基づく話者照合システムにおける合成音声による詐称の検討}, journal = {電子情報通信学会技術研究報告}, year = 1998, } @article{CTT100423287, author = {Takashi Masuko and Takao Kobayashi and Masatsune Tamura and Jun Masubuchi and Keiichi Tokuda}, title = {Text-to-Visual Speech Synthesis Based on Parameter Generation from HMM}, journal = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 1998, } @article{CTT100423286, author = {Keiichi Tokuda and Takashi Masuko and Jun Hiroi and Takao Kobayashi and Tadashi Kitamura}, title = {A Very Low Bit Rate Speech Coder Using HMM-Based Speech Recognition/Synthesis}, journal = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 1998, } @article{CTT100423285, author = {Kazuhito Koishida and Gou Hirabayashi and Keiichi Tokuda and Takao Kobayashi}, title = {A Wideband CELP Speech Coder at 16 kbit/s Based on Mel-Generalized Cepstral Analysis}, journal = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing}, year = 1998, } @article{CTT100423284, author = {Masatsune Tamura and Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {Speaker Adaptation for HMM-based Speech Synthesis System Using MLLR}, journal = {Proceedings of 3rd ESCA/ COSCOSDA International Workshop on Speech Synthesis}, year = 1998, } @article{CTT100423273, author = {Kazuhito Koishida and Gou Hirabayashi and Keiichi Tokuda and Takao Kobayashi}, title = {A 16kbit/s Wideband CELP Coder Using Mel-Generalized Cepstral Analysis and Its Subjective Evaluation}, journal = {Proceedings of 5th International Conference on Spoken Language Processing}, year = 1998, } @article{CTT100423272, author = {Takashi Masuko and Keiichi Tokuda and Takao Kobayashi}, title = {A Very Low Bit Rate Speech Coder Using HMM with Speaker Adaptation}, journal = {Proceedings of 5th International Conference on Spoken Language Processing}, year = 1998, } @article{CTT100423271, author = {Takayoshi Yoshimura and Takashi Masuko and Keiichi Tokuda and Takao Kobayashi and Tadashi Kitamura}, title = {Duration Modeling for HMM-based Speech Synthesis}, journal = {Proceedings of 5th International Conference on Spoken Language Processing}, year = 1998, } @article{CTT100423269, author = {Masatsune Tamura and Takashi Masuko and Takao Kobayashi and Keiichi Tokuda}, title = {Visual Speech Ssynthesis Based on Parameter Generation from HMM: Speech-Driven and Text-and-Speech-Driven Approaches}, journal = {Proceedings of International Conference on Auditory-Visual Speech Processing}, year = 1998, } @article{CTT100486039, author = {小林隆夫}, title = {HMMに基づく音声合成システムにおける話者補間}, journal = {日本音響学会平成9年度秋季研究発表会講演論文集}, year = 1997, } @article{CTT100486038, author = {小林隆夫}, title = {HMMに基づくテキストから唇動画像生成}, journal = {日本音響学会平成9年度秋季研究発表会講演論文集}, year = 1997, } @article{CTT100486037, author = {小林隆夫}, title = {音声パラメータの静的・動的特徴の統計量を用いたベクトル量子化の検討}, journal = {日本音響学会平成9年度秋季研究発表会講演論文集}, year = 1997, } @article{CTT100474851, author = {小林隆夫}, title = {HMMに基づいた極低ビットレート音声符号化}, journal = {日本音響学会平成9年度秋季研究発表会講演論文集}, year = 1997, } @article{CTT100474850, author = {小林隆夫}, title = {対数スペクトルの任意基底関数による展開に基づいた音声のスペクトル推定}, journal = {日本音響学会平成9年度秋季研究発表会講演論文集}, year = 1997, } @article{CTT100486036, author = {小林隆夫}, title = {ML基準パラメータ系列生成に基づく半連続HMMの雑音適応手法の評価}, journal = {日本音響学会平成9年度秋季研究発表会講演論文集}, year = 1997, } @article{CTT100486023, author = {小林隆夫}, title = {動的特徴を用いたHMMからの音声パラメータ生成アルゴリズム}, journal = {日本音響学会誌}, year = 1997, } @article{CTT100486024, author = {小林隆夫}, title = {メル一般化ケプストラム係数に基づく音声のスペクトル表現とその諸特性}, journal = {電子情報通信学会論文誌}, year = 1997, } @article{CTT100486025, author = {Takao Kobayashi}, title = {The IF Spectrogram : A New Spectral Representation}, journal = {Proceedings of International Symposium on Simulation, Visualization and Auralization for Acoustics Research and Education}, year = 1997, } @article{CTT100486026, author = {Takao Kobayashi}, title = {Efficient Encoding of Mel-Generalized Cepstrum for CELP Coders}, journal = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 1997, } @article{CTT100486027, author = {Takashi Masuko and Keiichi Tokuda and Takao Kobayashi and Satoshi Imai}, title = {Voice Characteristics Conversion for HMM-based Speech Synthesis System}, journal = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 1997, } @article{CTT100486028, author = {Kazuhito Koishida and Keiichi Tokuda and Takashi Masuko and Takao Kobayashi}, title = {Vector Quantization of Speech Spectral Parameters Using Statistics of Dynamic Features}, journal = {Proceedings of International Conference on Speech Processing}, year = 1997, } @article{CTT100486029, author = {Takao Kobayashi}, title = {Spectral Quantization Using Statistics of Static and Dynamic Features}, journal = {1997 IEEE Workshop on Speech Coding for Telecommunications Proceedings}, year = 1997, } @article{CTT100486030, author = {Takao Kobayashi}, title = {HMM Compensation for Noisy Speech Recognition Based on Cepstral Parameter Generation}, journal = {Proceedings 5th European Conference on Speech Communication and Technology}, year = 1997, } @article{CTT100486031, author = {Takao Kobayashi}, title = {Speaker Iinterpolation in HMM-Based Speech Synthesis System}, journal = {Proceedings 5th European Conference on Speech Communication and Technology}, year = 1997, } @article{CTT100486032, author = {小林隆夫}, title = {HMMを用いた唇動画像の生成}, journal = {電子情報通信学会技術研究報告}, year = 1997, } @article{CTT100486033, author = {小林隆夫}, title = {メル一般化ケプストラム分析に基づく広帯域音声のCELP符号化の検討}, journal = {電子情報通信学会技術研究報告}, year = 1997, } @article{CTT100486034, author = {小林隆夫}, title = {HMMを用いた音声合成における話者適応による声質変換}, journal = {日本音響学会平成9年度春季研究発表会講演論文集}, year = 1997, } @article{CTT100486035, author = {小林隆夫}, title = {自己組織化Feature Mapに基づいたHMMとその音声認識への応用}, journal = {日本音響学会平成9年度秋季研究発表会講演論文集}, year = 1997, } @article{CTT100486016, author = {江川 護 and 小林 隆夫 and 今井 聖}, title = {改良DFT-MUSIC法を用いた低SNR環境における瞬時周波数の推定}, journal = {電子情報通信学会1996年総合大会講演論文集}, year = 1996, } @article{CTT100486004, author = {阿部 敏彦 and 小林 隆夫 and 今井 聖}, title = {瞬時周波数に基づく雑音環境下でのピッチ推定}, journal = {電子情報通信学会論文誌}, year = 1996, } @article{CTT100486005, author = {益子 貴史 and 徳田 恵一 and 小林 隆夫 and 今井 聖}, title = {動的特徴を用いたHMMに基づく音声合成}, journal = {電子情報通信学会論文誌}, year = 1996, } @article{CTT100486006, author = {Takashi Masuko and Keiichi Tokuda and Takao Kobayashi and Satoshi Imai}, title = {Speech Synthesis Using HMMs with Dynamic Features}, journal = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 1996, } @article{CTT100486007, author = {Kazuhito Koishida and Keiichi Tokuda and Takao Kobayashi and Satoshi Imai}, title = {CELP Coding System Based on Mel-Generalized Cepstral Analysis}, journal = {Proceedings of 4th International Conference on Spoken Language Processing}, year = 1996, } @article{CTT100486008, author = {Takao Kobayashi}, title = {Robust Pitch Estimation with Harmonic Enhancement in Noisy Environment Based on Instantaneous Frequency}, journal = {Proceedings of 4th International Conference on Spoken Language Processing}, year = 1996, } @article{CTT100486009, author = {Takao Kobayashi}, title = {Spectral Representation of Speech Using Mel-Generalized Cepstral Coefficients}, journal = {Journal of the Acoustical Society of America}, year = 1996, } @article{CTT100486010, author = {Takashi Masuko and Keiichi Tokuda and Takao Kobayashi and Satoshi Imai}, title = {HMM-Based Speech Synthesis with Various Voice Characteristics}, journal = {Journal of the Acoustical Society of America}, year = 1996, } @article{CTT100486011, author = {Takao Kobayashi}, title = {Quantization of Vector Sequences Using Statistics of Neighboring Input Vectors}, journal = {Journal of the Acoustical Society of America}, year = 1996, } @article{CTT100486012, author = {Takao Kobayashi and Takashi Masuko and Keiichi Tokuda and Satoshi Imai}, title = {Noisy Speech Recognition Using HMM-Based Cepstral Parameter Generation and Compensation}, journal = {Journal of the Acoustical Society of America}, year = 1996, } @article{CTT100486013, author = {小林隆夫}, title = {HMMからの音声パラメータ生成アルゴリズム}, journal = {電子情報通信学会技術研究報告}, year = 1996, } @article{CTT100486014, author = {益子 貴史 and 徳田 恵一 and 小林 隆夫 and 今井 聖}, title = {メルケプストラムをパラメータとするHMMに基づく音声合成}, journal = {電子情報通信学会技術研究報告}, year = 1996, } @article{CTT100486015, author = {Takao Kobayashi}, title = {Hybrid Learning for Radial Basis Function Networks}, journal = {Technical Report of IEICE}, year = 1996, } @article{CTT100486017, author = {小林隆夫}, title = {HMMを用いた音声合成における音素モデルの検討}, journal = {日本音響学会平成8年度春季研究発表会講演論文集}, year = 1996, } @article{CTT100486018, author = {小林隆夫}, title = {メル一般化ケプストラムに基づくCELP符号化系とその評価}, journal = {日本音響学会平成8年度春季研究発表会講演論文集}, year = 1996, } @article{CTT100486019, author = {小林隆夫}, title = {音声信号の瞬時周波数に基づく振幅スペクトル表現}, journal = {日本音響学会平成8年度春季研究発表会講演論文集}, year = 1996, } @article{CTT100486020, author = {小林隆夫}, title = {ML基準パラメータ系列生成に基づくHMMの雑音環境への適応}, journal = {日本音響学会平成8年度秋季研究発表会講演論文集}, year = 1996, } @article{CTT100486021, author = {小林隆夫}, title = {ML基準パラメータ系列生成に基づく半連続HMMによる雑音音声認識}, journal = {日本音響学会平成8年度秋季研究発表会講演論文集}, year = 1996, } @article{CTT100486022, author = {小林隆夫}, title = {MA予測を用いたメル一般化ケプストラムの量子化}, journal = {日本音響学会平成8年度秋季研究発表会講演論文集}, year = 1996, } @article{CTT100485998, author = {小林隆夫}, title = {雑音環境下での瞬時周波数推定}, journal = {電子情報通信学会技術研究報告書}, year = 1995, } @article{CTT100486003, author = {小林隆夫}, title = {メル一般化ケプストラム分析に基づく音声符号化の検討}, journal = {日本音響学会平成7年度秋季研究発表会講演論文集}, year = 1995, } @article{CTT100486002, author = {小林隆夫}, title = {HMMを用いた音声合成法に関する検討}, journal = {日本音響学会平成7年度秋季研究発表会講演論文集}, year = 1995, } @article{CTT100486001, author = {小林隆夫}, title = {音声信号の非線形伸縮と瞬時周波数に基づく倍音推定}, journal = {日本音響学会平成7年度春季研究発表会講演論文集}, year = 1995, } @article{CTT100486000, author = {小林隆夫}, title = {低ビット音声符号化のためのメルケプストラム係数のベクトル量子化}, journal = {日本音響学会平成7年度春季研究発表会講演論文集}, year = 1995, } @article{CTT100485999, author = {小林隆夫}, title = {メル一般化ケプストラムパラメータの音素認識における評価}, journal = {日本音響学会平成7年度春季研究発表会講演論文集}, year = 1995, } @article{CTT100475248, author = {Takao Kobayashi}, title = {Harmonic Estimation Based on Instantaneous Frequency and Its Application to Pitch Determination of Speech}, journal = {IEICE Transactions on Information and System}, year = 1995, } @article{CTT100475249, author = {Takao Kobayashi}, title = {Adaptive Cepstral Analysis of Speech}, journal = {IEEE Transactions on Speech and Audio Processing}, year = 1995, } @article{CTT100475250, author = {Takao Kobayashi}, title = {CELP Coding Based on Mel-Cepstral Analysis}, journal = {Proceedings of 1995 International Conference on Acoustics, Speech and Signal Processing}, year = 1995, } @article{CTT100475251, author = {Takao Kobayashi}, title = {Speech Parameter Generation form HMM using Dynamic Features}, journal = {Proceedings of 1995 International Conference on Acoustics, Speech and Signal Processing}, year = 1995, } @article{CTT100475252, author = {Takao Kobayashi}, title = {Harmonic Tracking and Pitch Extraction Based on Instantaneous Frequency}, journal = {Proceedings of 1995 International Conference on Acoustics, Speech and Signal Processing}, year = 1995, } @article{CTT100475253, author = {Takao Kobayashi}, title = {an Algorithm for Speech Parameter Generation form Continuous Mixture HMM With Dynamic Features}, journal = {Proceedings of 4th European Conference on Speech Communication and Technology}, year = 1995, } @article{CTT100485994, author = {小林隆夫}, title = {時間軸伸縮を導入した瞬時周波数に基づく倍音推定}, journal = {電子情報通信学会技術研究報告書}, year = 1995, } @article{CTT100485995, author = {小林隆夫}, title = {メル一般化ケプストラムをパラメータによる音声のスペクトル表現とその諸特性}, journal = {電子情報通信学会技術研究報告書}, year = 1995, } @article{CTT100485996, author = {小林隆夫}, title = {メル一般化ケプストラム分析に基づくCELP符号化}, journal = {電子情報通信学会技術研究報告書}, year = 1995, } @article{CTT100485997, author = {小林隆夫}, title = {瞬時周波数に基づく雑音環境下でのピッチ推定}, journal = {電子情報通信学会技術研究報告書}, year = 1995, } @article{CTT100485990, author = {Takao Kobayashi}, title = {Speech Coding Based on Adaptive Mel-Cepstral Analysis}, journal = {Proceedings of 1994 International Conference on Acoustics, Speech & Signal Processing}, year = 1994, } @article{CTT100485991, author = {Takao Kobayashi}, title = {Mel-Generalized Cepstral Analysis-A Unified Approach to Speech Spectral Estimation}, journal = {Proceedings of 1994 International Conference on Spoken Language Processing}, year = 1994, } @article{CTT100485993, author = {小林隆夫}, title = {適応メルケプストラム分析を利用した音声符号化とその評価}, journal = {電子情報通信学会論文誌A}, year = 1994, } @article{CTT100485992, author = {Takao Kobayashi}, title = {Speech Coding Based on Adaptive Mel-Cepstral Analysis for Noisy Channels}, journal = {Proceedings of 1994 International Conference on Spoken Language Processing}, year = 1994, } @article{CTT100485989, author = {小林隆夫}, title = {雑音劣化音声の一般化ケプストラムモデル化における事前情報の利用}, journal = {電子情報通信学会論文誌A}, year = 1994, } @article{CTT100485987, author = {Takao Kobayashi}, title = {Generalized Cepstral Modeling of Degraded Speech and Its Application to Speech Enhancement}, journal = {IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences}, year = 1993, } @article{CTT100485988, author = {Takao Kobayashi}, title = {Generalized Cepstral Modeling of Speech Degraded by Additive Noise}, journal = {Proceedings of European Conterence on Speech Communication and Technology}, year = 1993, } @article{CTT100485985, author = {小林隆夫}, title = {メル一般化ケプストラム分析による音声のスペクトル推定}, journal = {電子情報通信学会論文誌}, year = 1992, } @article{CTT100485982, author = {Takao Kobayashi}, title = {2-D LMA Filters-Design of Stable Two-Dimensional Digital Filters with Arbitrary Magnitude Function}, journal = {IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences}, year = 1992, } @article{CTT100485986, author = {小林隆夫}, title = {メルケプストラムをパラメータとする音声のスペクトル推定}, journal = {電子情報通信学会論文誌}, year = 1991, } @article{CTT100485979, author = {Takao Kobayashi}, title = {Design of IIR Digital Filters with Arbitrary Log Magnitude Function by WLS Techniques}, journal = {IEEE Transactions on Acoustics, Speech, and Signal Processing}, year = 1990, } @article{CTT100485983, author = {小林隆夫}, title = {適応ケプストラム分析-ケプストラムを係数とする適応フィルター}, journal = {電子情報通信学会論文誌}, year = 1990, } @article{CTT100485978, author = {小林隆夫}, title = {一般化ケプストラムをパラメータとする音声のスペクトル推定}, journal = {電子情報通信学会論文誌}, year = 1989, } @article{CTT100485980, author = {Takao Kobayashi}, title = {Complex Chebyshev Approximation for IIR Digital Filters with Arbitrary Log Magnitude and Phase Functions}, journal = {Transactions of the Institute of Electronics, Information and Communication Engineers}, year = 1989, } @article{CTT100485984, author = {小林隆夫}, title = {単語音声認識における一般化ケプストラム距離尺度の検討}, journal = {電子情報通信学会論文誌}, year = 1988, } @article{CTT100485981, author = {小林隆夫}, title = {一般化ケプストラム距離尺度}, journal = {電子通信学会論文誌}, year = 1986, } @article{CTT100485977, author = {Takao Kobayashi}, title = {Spectral Analysis Using Generalized Cepstrum}, journal = {IEEE Transactions on Acoustics, Speech, and Signal Processing}, year = 1984, } @inproceedings{CTT100815909, author = {Tomoki Koriyama and Takao Kobayashi}, title = {Semi-supervised prosody modeling using deep Gaussian process latent variable model}, booktitle = {Proc. 20th Annual Conference of the International Speech Communication (INTERSPEECH 2019)}, year = 2019, } @inproceedings{CTT100815910, author = {Tomoki Koriyama and Shinnosuke Takamichi and Takao Kobayashi}, title = {Sparse Approximation of Gram Matrices for GMMN-based Speech Synthesis}, booktitle = {Proc. SSW10}, year = 2019, } @inproceedings{CTT100815926, author = {蛭田宜樹 and 郡山知樹 and 小林隆夫}, title = {DNN音声合成におけるスタイル付与モデル学習法の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2019, } @inproceedings{CTT100815908, author = {Tomoki Koriyama and Takao Kobayashi}, title = {A training method using DNN-guided layerwise pretraining for deep Gaussian processes}, booktitle = {Proc. 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019)}, year = 2019, } @inproceedings{CTT100815905, author = {成田昂世 and 郡山知樹 and 小林隆夫 and 井島勇祐}, title = {対話情報を考慮した韻律生成の検討}, booktitle = {日本音響学会2019年春季研究発表会講演論文集}, year = 2019, } @inproceedings{CTT100815906, author = {蛭田宜樹 and 郡山知樹 and 太刀岡勇気 and 小林隆夫}, title = {DNN音声合成における少量の学習データを用いたスタイル付与の検討}, booktitle = {日本音響学会2019年春季研究発表会講演論文集}, year = 2019, } @inproceedings{CTT100815903, author = {郡山知樹 and 高道慎之介 and 小林隆夫}, title = {グラム行列のスパース近似を用いた生成的モーメントマッチングネットに基づく音声合成の検討}, booktitle = {日本音響学会2019年春季研究発表会講演論文集}, year = 2019, } @inproceedings{CTT100815893, author = {郡山知樹 and 小林隆夫}, title = {深層ガウス過程とアクセントの潜在変数表現に基づく音声合成の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2019, } @inproceedings{CTT100815895, author = {郡山知樹 and 高道慎之介 and 小林隆夫}, title = {GMMNに基づく音声合成におけるグラム行列のスパース近似の検討}, booktitle = {情報処理学会研究報告}, year = 2019, } @inproceedings{CTT100815896, author = {蛭田宜樹 and 郡山知樹 and 小林隆夫}, title = {ガウス過程回帰に基づくオーディオブック音声合成の評価}, booktitle = {日本音響学会2018年秋季研究発表会講演論文集}, year = 2018, } @inproceedings{CTT100815898, author = {郡山知樹 and 小林隆夫}, title = {深層ガウス過程に基づく音声合成のための事前学習の検討}, booktitle = {日本音響学会2018年秋季研究発表会講演論文集}, year = 2018, } @inproceedings{CTT100760841, author = {郡山知樹 and 小林隆夫}, title = {GPR音声合成における深層構造の利用の検討}, booktitle = {日本音響学会2018年春季研究発表会講演論文集}, year = 2018, } @inproceedings{CTT100760842, author = {前野雄也 and 郡山知樹 and 小林隆夫}, title = {GPR音声合成における区分線形変換を用いたスタイル適応のためのデータ分割法の検討}, booktitle = {日本音響学会2018年春季研究発表会講演論文集}, year = 2018, } @inproceedings{CTT100760843, author = {郡山知樹 and 小林隆夫}, title = {GPR音声合成における深層ガウス過程の利用の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2018, } @inproceedings{CTT100758688, author = {郡山知樹 and 小林隆夫}, title = {GP-DNNハイブリッドモデルに基づく統計的音声合成の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2018, } @inproceedings{CTT100758687, author = {Nattapong Kurpukdee and Tomoki Koriyama and Takao Kobayashi and Sawit Kasuriya and Chai Wutiwiwatchai and Poonlap Lamsrichan}, title = {Speech emotion recognition using convolutional long short-term memory neural network and support vector machines}, booktitle = {Proc. 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference}, year = 2017, } @inproceedings{CTT100770751, author = {小林隆夫}, title = {表現豊かな音声合成に向けた多様な話者性とスタイルによる音声合成への取組み}, booktitle = {電子情報通信学会技術研究報告}, year = 2017, } @inproceedings{CTT100758686, author = {Decha Moungsri and Tomoki Koriyama and Takao Kobayashi}, title = {Enhanced F0 generation for GPR-based speech synthesis considering syllable-based prosodic features}, booktitle = {Proc. 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference}, year = 2017, } @inproceedings{CTT100753523, author = {郡山知樹 and 岡野 祐紀 and 小林隆夫}, title = {ガウス過程回帰に基づく歌声合成の検討}, booktitle = {日本音響学会2017年秋季研究発表会講演論文集}, year = 2017, } @inproceedings{CTT100753522, author = {郡山知樹 and 小林隆夫}, title = {GPR音声合成のためのフレームコンテキストカーネルに基づく決定木構築の検討}, booktitle = {日本音響学会2017年秋季研究発表会講演論文集}, year = 2017, } @inproceedings{CTT100737523, author = {Decha Moungsri and Tomoki Koriyama and Takao Kobayashi}, title = {Duration Prediction Using Multiple Gaussian Process Experts For GPR-based Speech Synthesis}, booktitle = {Proc. 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017)}, year = 2017, } @inproceedings{CTT100737526, author = {津野駿幸 and 郡山知樹 and 小林隆夫}, title = {GPR音声合成に基づいたオーディオブック音声の合成}, booktitle = {日本音響学会2017年春季研究発表会講演論文集}, year = 2017, } @inproceedings{CTT100737527, author = {増子理菜 and 郡山知樹 and 小林隆夫}, title = {アクセント情報自動ラベリングの音声合成品質への影響に関する検討}, booktitle = {日本音響学会2017年春季研究発表会講演論文集}, year = 2017, } @inproceedings{CTT100737524, author = {高橋亮 and 郡山知樹 and 小林隆夫}, title = {コンテキストを考慮した音素マッチングに基づく非パラレルデータGMM声質変換}, booktitle = {日本音響学会2017年春季研究発表会講演論文集}, year = 2017, } @inproceedings{CTT100717204, author = {Decha Moungsri and Tomoki Koriyama and Takao Kobayashi}, title = {Unsupervised Stress Information Labeling Using Gaussian Process Latent Variable Model for Statistical Speech Synthesis}, booktitle = {Proc. 17th Annual Conference of the International Speech Communication (INTERSPEECH 2016)}, year = 2016, } @inproceedings{CTT100717207, author = {前野雄也 and 押尾翔平 and 郡山知樹 and 小林隆夫}, title = {GPR音声合成における区分線形特徴量変換を用いたスタイル適応の検討}, booktitle = {日本音響学会2016年秋季研究発表会講演論文集}, year = 2016, } @inproceedings{CTT100717206, author = {高橋亮 and 郡山知樹 and 小林隆夫}, title = {非パラレルデータを用いるGMM声質変換の検討}, booktitle = {日本音響学会2016年秋季研究発表会講演論文集}, year = 2016, } @inproceedings{CTT100717205, author = {Decha Moungsri and Tomoki Koriyama and Takao Kobayashi}, title = {Tone modeling using Gaussian process latent variable model for statistical speech synthesis}, booktitle = {Proc. Speech Prosody 2016}, year = 2016, } @inproceedings{CTT100703192, author = {前野雄也 and 郡山知樹 and 小林隆夫}, title = {GPR音声合成におけるスタイル適応の検討}, booktitle = {日本音響学会2016年春季研究発表会講演論文集}, year = 2016, } @inproceedings{CTT100703189, author = {Tomoki Koriyama and Syohei Oshio and Takao Kobayashi}, title = {A Speaker Adaptation Technique For Gaussian Process Regression Based Speech Synthesis Using Feature Space Transform}, booktitle = {Proc. 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016)}, year = 2016, } @inproceedings{CTT100717208, author = {岡元伶洋 and 郡山知樹 and 小林隆夫}, title = {多様なスタイルによるGPR音声合成の検討}, booktitle = {日本音響学会2016年春季研究発表会講演論文集}, year = 2016, } @inproceedings{CTT100703194, author = {増子理菜 and 郡山知樹 and 小林隆夫}, title = {音声合成のためのCRF/HMMに基づく自動アクセント推定の評価}, booktitle = {電子情報通信学会技術研究報告}, year = 2016, } @inproceedings{CTT100696876, author = {押尾翔平 and 郡山知樹 and 小林隆夫}, title = {GPR音声合成における話者適応手法の検討}, booktitle = {日本音響学会2015年秋季研究発表会講演論文集}, year = 2015, } @inproceedings{CTT100696874, author = {Tomoki Koriyama and Takao Kobayashi}, title = {A comparison of speech synthesis systems based on GPR, HMM, and DNN with a small amount of training data}, booktitle = {Proc. 16th Annual Conference of the International Speech Communication}, year = 2015, } @inproceedings{CTT100715061, author = {Takashi Nose and Yusuke Arao and Takao Kobayashi and Komei Sugiura and Yoshinori Shiga and Akinori Ito}, title = {Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts}, booktitle = {Proc. 16th Annual Conference of the International Speech Communication}, year = 2015, } @inproceedings{CTT100696875, author = {郡山知樹 and 小林隆夫}, title = {ガウス過程回帰に基づく音声合成システムの評価}, booktitle = {日本音響学会2015年秋季研究発表会講演論文集}, year = 2015, } @inproceedings{CTT100696873, author = {Decha Moungsri and Tomoki Koriyama and Takao Kobayashi}, title = {Duration prediction using multi-level model for GPR-based speech synthesis}, booktitle = {Proc. 16th Annual Conference of the International Speech Communication}, year = 2015, } @inproceedings{CTT100715075, author = {能勢 隆 and 荒生 侑介 and 小林 隆夫 and 杉浦 孔明 and 志賀 芳則}, title = {統計的音声合成におけるエントロピーに基づく大規模学習文セット構築の評価}, booktitle = {電子情報通信学会技術研究報告}, year = 2015, } @inproceedings{CTT100686444, author = {Tomoki Koriyama and Takao Kobayashi}, title = {Prosody Generation Using Frame-based Gaussian Process Regression and Classification for Statistical Parametric Speech Synthesis}, booktitle = {Proc. ICASSP 2015}, year = 2015, } @inproceedings{CTT100841915, author = {増子 理菜 and 郡山 知樹 and 篠崎 隆宏 and 小林 隆夫}, title = {言語モデルと音響モデルを用いた自動韻律ラベリングの評価}, booktitle = {日本音響学会2015年春季研究発表会講演論文集}, year = 2015, } @inproceedings{CTT100686447, author = {岡元伶洋 and 郡山知樹 and 小林隆夫}, title = {ガウス過程回帰に基づく音声合成のためのコンテキストの検討}, booktitle = {日本音響学会2015年春季研究発表会講演論文集}, year = 2015, } @inproceedings{CTT100686445, author = {郡山知樹 and 小林隆夫}, title = {ガウス過程回帰に基づく音声合成システムの検討}, booktitle = {日本音響学会2015年春季研究発表会講演論文集}, year = 2015, } @inproceedings{CTT100681150, author = {Decha Moungsri and Tomoki Koriyama and Takao Kobayashi}, title = {HMM-based Thai speech synthesis using unsupervised stress context labeling}, booktitle = {Proc. 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference}, year = 2014, } @inproceedings{CTT100754262, author = {小林 友哉 and 能勢 隆 and 篠崎 隆宏 and 小林 隆夫}, title = {GMMに基づく声質変換のためのMDL基準による混合数の自動決定}, booktitle = {秋季講演論文集}, year = 2014, } @inproceedings{CTT100754243, author = {博多屋 涼 and 篠崎隆宏 and 小林隆夫}, title = {ボルツマンマシンとMCMCサンプリングを用いた音声のシングルチャネル雑音除去}, booktitle = {秋季研究発表会講演論文集}, year = 2014, } @inproceedings{CTT100754249, author = {房 福明 and 篠崎隆宏 and 小林隆夫}, title = {スイッチ入力音声コミュニケーション支援システムのための入力プロトコル推薦手法}, booktitle = {秋季研究発表会講演論文集}, year = 2014, } @inproceedings{CTT100677070, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {ガウス過程回帰に基づくF0パタン生成の検討}, booktitle = {日本音響学会2014年秋期研究発表会講演論文集}, year = 2014, } @inproceedings{CTT100677069, author = {Daiki Nagahama and Takashi Nose and Tomoki Koriyama and Takao Kobayashi}, title = {Transform mapping using shared decision tree context clustering for HMM-based cross-lingual speech synthesis}, booktitle = {Proc. INTERSPEECH 2014}, year = 2014, } @inproceedings{CTT100677068, author = {Tomoki Koriyama and Hiroshi Suzuki and Takashi Nose and Takahiro Shinozaki and Takao Kobayashi}, title = {Accent Type and Phrase Boundary Estimation Using Acoustic and Language Models for Automatic Prosodic Labeling}, booktitle = {Proc. INTERSPEECH 2014}, year = 2014, } @inproceedings{CTT100677067, author = {Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {Parametric Speech Synthesis Using Local and Global Sparse Gaussian Processes}, booktitle = {Proc. The 24th IEEE International Workshop on Machine Learning for Signal Processing}, year = 2014, } @inproceedings{CTT100754263, author = {荒生 侑介 and 能勢 隆 and 篠崎 隆宏 and 小林 隆夫}, title = {複数ドメインコーパスからの文選択に基づくキャラクター音声合成の検討}, booktitle = {秋季講演論文集}, year = 2014, } @inproceedings{CTT100744958, author = {房福明 and 篠崎 隆宏 and 小林隆夫}, title = {スイッチ入力音声合成システムのための仮名プロトコル推薦手法}, booktitle = {電子情報通信学会技術研究報告 = IEICE technical report : 信学技報}, year = 2014, } @inproceedings{CTT100668124, author = {Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {Parametric Speech Synthesis Based on Gaussian Process Regression Using Global Variance and Hyperparameter Optimization}, booktitle = {Proc. ICASSP 2014}, year = 2014, } @inproceedings{CTT100672912, author = {Decha Moungsri and Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {Tone Modeling Using Stress Information for HMM-Based Thai Speech Synthesis}, booktitle = {Proc. Speech Prosody 2014}, year = 2014, } @inproceedings{CTT100668127, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {系列内変動を考慮したガウス過程回帰に基づく音声パラメータ生成}, booktitle = {日本音響学会2014年春季研究発表会講演論文集}, year = 2014, } @inproceedings{CTT100668128, author = {荒生侑介 and 能勢 隆 and 郡山知樹 and 篠崎隆宏 and 小林隆夫}, title = {音声合成のための音韻・韻律コンテキストを考慮した文選択アルゴリズムの評価}, booktitle = {日本音響学会2014年春季研究発表会講演論文集}, year = 2014, } @inproceedings{CTT100668131, author = {長濱大樹 and 能勢 隆 and 郡山知樹 and 小林隆夫}, title = {共有決定木を利用した話者適応に基づくクロスリンガル音声合成の評価}, booktitle = {日本音響学会2014年春季研究発表会講演論文集}, year = 2014, } @inproceedings{CTT100668130, author = {大西浩之 and 能勢 隆 and 郡山知樹 and 小林隆夫}, title = {HMM音声合成における正規化学習を用いたアクセント誤り削減の検討}, booktitle = {日本音響学会2014年春季研究発表会講演論文集}, year = 2014, } @inproceedings{CTT100668129, author = {舘野英樹 and 能勢 隆 and 郡山知樹 and 篠崎隆宏 and 小林隆夫}, title = {HMM音声合成のための音節出現頻度にロバストな音素セットの検討}, booktitle = {日本音響学会2014年春季研究発表会講演論文集}, year = 2014, } @inproceedings{CTT100668132, author = {鈴木啓史 and 郡山知樹 and 能勢 隆 and 篠崎隆宏 and 小林隆夫}, title = {音響モデルと言語モデルを利用したアクセント型・アクセント句境界の同時推定}, booktitle = {日本音響学会2014年春季研究発表会講演論文集}, year = 2014, } @inproceedings{CTT100668134, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {ガウス過程回帰に基づく音声合成におけるハイパーパラメータ最適化の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2014, } @inproceedings{CTT100801450, author = {Nose, T. and Takao Kobayashi}, title = {Quantized f0 context and its applications to speech synthesis, speech coding, and voice conversion}, booktitle = {Proceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014}, year = 2014, } @inproceedings{CTT100801323, author = {Fang, F. and Takahiro Shinozaki and Takao Kobayashi}, title = {An automatic input protocol recommendation method for tailored switch-to-speech communication aid systems}, booktitle = {2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014}, year = 2014, } @inproceedings{CTT100668135, author = {鈴木啓史 and 郡山知樹 and 能勢 隆 and 篠崎隆宏 and 小林隆夫}, title = {言語モデルと音響モデルを利用したアクセント境界の自動推定}, booktitle = {電子情報通信学会技術研究報告}, year = 2013, } @inproceedings{CTT100802201, author = {小林隆夫}, title = {多様な音声合成に向けた取組みと課題(オーガナイズドセッション,第15回音声言語シンポジウム)}, booktitle = {電子情報通信学会技術研究報告. SP, 音声}, year = 2013, } @inproceedings{CTT100801892, author = {鈴木 啓史 and 郡山 智樹 and 能勢 隆 and 篠崎 隆宏 and 小林隆夫}, title = {言語モデルと音響モデルを利用したアクセント句境界の自動推定}, booktitle = {研究報告音声言語情報処理（SLP）}, year = 2013, } @inproceedings{CTT100801998, author = {小林隆夫}, title = {多様な音声合成に向けた取組みと課題}, booktitle = {研究報告音声言語情報処理（SLP）}, year = 2013, } @inproceedings{CTT100668133, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {スパース近似と畳み込みカーネルを用いたガウス過程回帰に基づく音声合成}, booktitle = {日本音響学会2013年秋期研究発表会講演論文集}, year = 2013, } @inproceedings{CTT100668126, author = {Takashi Nose and Misa Kanemoto and Tomoki Koriyama and Takao Kobayashi}, title = {A Style Control Technique for Singing Voice Synthesis Based on Multiple-regression HSMM}, booktitle = {Proc. INTERSPEECH 2013}, year = 2013, } @inproceedings{CTT100668125, author = {Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {Statistical nonparametric speech synthesis using sparse Gaussian processes}, booktitle = {Proc. INTERSPEECH 2013}, year = 2013, } @inproceedings{CTT100657343, author = {Yu Maeno and Takashi Nose and Takao Kobayashi and Tomoki Koriyama and Yusuke Ijima and Hideharu Nakajima and Hideyuki Mizuno and Osamu Yoshioka}, title = {HMM-based expressive speech synthesis based on phrase-level F0 context labeling}, booktitle = {Proc. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2013, } @inproceedings{CTT100657345, author = {Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {Frame-level acoustic modeling based on Gaussian process regression for statistical nonparametric speech synthesis}, booktitle = {Proc. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2013, } @inproceedings{CTT100657344, author = {Hiroki Kanagawa and Takashi Nose and Takao Kobayashi}, title = {Speaker-independent style conversion for HMM-based expressive speech synthesis}, booktitle = {Proc. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2013, } @inproceedings{CTT100652643, author = {金川裕紀 and 能勢 隆 and 小林隆夫}, title = {HMM音声合成における話者正規化学習を用いたスタイル変換法の評価}, booktitle = {日本音響学会2013年春季研究発表会講演論文集}, year = 2013, } @inproceedings{CTT100652645, author = {荒生侑介 and 能勢 隆 and 小林隆夫}, title = {対話音声合成のための音韻・韻律コンテキストを考慮した音声コーパス構築法の検討}, booktitle = {日本音響学会2013年春季研究発表会講演論文集}, year = 2013, } @inproceedings{CTT100652642, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {音声合成のためのガウス過程回帰を用いたフレームレベル音響モデリングの検討}, booktitle = {日本音響学会2013年春季研究発表会講演論文集}, year = 2013, } @inproceedings{CTT100648141, author = {能勢 隆 and 金本美沙 and 郡山知樹 and 小林隆夫}, title = {多様な歌声合成のための重回帰HSMMに基づくスタイル制御法の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2013, } @inproceedings{CTT100648142, author = {前野 悠 and 能勢 隆 and 小林隆夫 and 郡山知樹 and 井島勇祐 and 中嶋秀治 and 水野秀之 and 吉岡 理}, title = {多様な韻律生成のための多クラス局所韻律コンテキストの検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2013, } @inproceedings{CTT100648140, author = {金川裕紀 and 能勢 隆 and 小林隆夫}, title = {任意話者の多様なスタイル生成のための話者正規化スタイル変換法の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2013, } @inproceedings{CTT100645618, author = {能勢 隆 and CHUNWIJITRA VATAYA and 小林隆夫}, title = {HMM音声合成におけるスペクトル特徴量の局所変動のモデル化とパラメータ生成への適用}, booktitle = {電子情報通信学会技術研究報告}, year = 2012, } @inproceedings{CTT100644238, author = {Vataya Chunwijitra and Takashi Nose and Takao Kobayashi}, title = {A speech parameter generation algorithm using local variance for HMM-based speech synthesis}, booktitle = {Proc. 13th Annual Conference of the International Speech Communication Association}, year = 2012, } @inproceedings{CTT100644242, author = {金川裕紀 and 能勢 隆 and 小林隆夫}, title = {HMM音声合成における不特定話者スタイル変換のための話者正規化学習法の検討}, booktitle = {日本音響学会2012年秋季研究発表会講演論文集}, year = 2012, } @inproceedings{CTT100644241, author = {能勢 隆 and 小林隆夫}, title = {共有決定木を利用した話者適応に基づくクロスリンガル音声合成の検討}, booktitle = {日本音響学会2012年秋季研究発表会講演論文集}, year = 2012, } @inproceedings{CTT100644240, author = {能勢 隆 and ワータヤー・チュンウィジター and 小林隆夫}, title = {HMM音声合成のための局所的系列内変動を考慮したパラメータ生成の検討}, booktitle = {日本音響学会2012年秋季研究発表会講演論文集}, year = 2012, } @inproceedings{CTT100644237, author = {Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {Discontinuous observation HMM for prosodic-event-based F0 generation}, booktitle = {Proc. 13th Annual Conference of the International Speech Communication Association}, year = 2012, } @inproceedings{CTT100640305, author = {前野 悠 and 能勢 隆 and 小林 隆夫 and 井島 勇祐 and 中嶋 秀治 and 水野 秀之 and 吉岡 理}, title = {強調音声合成のための局所韻律コンテキスト自動付与の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2012, } @inproceedings{CTT100636072, author = {Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {An F0 modeling technique based on prosodic events for spontaneous speech synthesis}, booktitle = {Proc. 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2012, } @inproceedings{CTT100634463, author = {郡山 知樹 and 能勢 隆 and 小林隆夫}, title = {観測値の不連続性を考慮したHMMに基づくF0モデル化の検討}, booktitle = {日本音響学会2012年春季研究発表会講演論文集}, year = 2012, } @inproceedings{CTT100634464, author = {能勢 隆 and 小林隆夫}, title = {合成音声のスタイル制御における系列内変動を考慮したスペクトル・韻律パラメータの生成}, booktitle = {日本音響学会2012年春季研究発表会講演論文集}, year = 2012, } @inproceedings{CTT100632235, author = {能勢 隆 and 小林隆夫}, title = {HMM音声合成のための動的特徴量を用いた音素継続長モデリングの検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2011, } @inproceedings{CTT100632234, author = {金川裕紀 and 能勢 隆 and 小林隆夫}, title = {HMM音声合成における不特定話者スタイル変換の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2011, } @inproceedings{CTT100632233, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {韻律イベントHMMを用いた対話音声F0生成}, booktitle = {電子情報通信学会技術研究報告}, year = 2011, } @inproceedings{CTT100630556, author = {Takashi Nose and Takao Kobayashi}, title = {Recent development of HMM-based expressive speech synthesis and its applications}, booktitle = {Proc. 2011 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2011)}, year = 2011, } @inproceedings{CTT100630075, author = {太刀岡 勇気 and 堀井 昭男 and 岩崎 知弘 and 斉藤 辰彦 and 能勢 隆 and 小林隆夫}, title = {音声合成を用いた音声認識性能予測 − 残響と騒音が存在する環境での評価 −}, booktitle = {日本音響学会2011年秋季研究発表会講演論文集}, year = 2011, } @inproceedings{CTT100630078, author = {前野 悠 and 能勢 隆 and 小林隆夫 and 井島 勇祐 and 中嶋 秀治 and 水野 秀之 and 吉岡 理}, title = {多様な音声合成のための強調コンテキストの自動付与の検討}, booktitle = {日本音響学会2011年秋季研究発表会講演論文集}, year = 2011, } @inproceedings{CTT100630077, author = {郡山 知樹 and 能勢 隆 and 小林隆夫}, title = {対話音声合成のためのイントネーションラベルのタイミング予測}, booktitle = {日本音響学会2011年秋季研究発表会講演論文集}, year = 2011, } @inproceedings{CTT100630076, author = {能勢 隆 and 小林隆夫}, title = {感情音声合成における主観的表出度合のモデル化と制御の検討}, booktitle = {日本音響学会2011年秋季研究発表会講演論文集}, year = 2011, } @inproceedings{CTT100627749, author = {Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {On the use of extended context for HMM-based spontaneous conversational speech synthesis}, booktitle = {Proc. 12th Annual Conference of the International Speech Communication Association}, year = 2011, } @inproceedings{CTT100627746, author = {Takashi Nose and Takao Kobayashi}, title = {A perceptual expressivity modeling technique for speech synthesis based on multiple-regression HSMM}, booktitle = {Proc. 12th Annual Conference of the International Speech Communication Association}, year = 2011, } @inproceedings{CTT100627747, author = {Yu Maeno and Takashi Nose and Takao Kobayashi and Yusuke Ijima and Hideharu Nakajima and Hideyuki Mizuno and Osamu Yoshioka}, title = {HMM-based emphatic speech synthesis using unsupervised context labeling}, booktitle = {Proc. 12th Annual Conference of the International Speech Communication Association}, year = 2011, } @inproceedings{CTT100627748, author = {Tatsuhiko Saito and Takashi Nose and Takao Kobayashi and Yohei Okato and Akio Horii}, title = {Performance prediction of speech recognition using average-voice-based speech synthesis}, booktitle = {Proc. 12th Annual Conference of the International Speech Communication Association}, year = 2011, } @inproceedings{CTT100622329, author = {Vataya Chunwijitra and Takashi Nose and Takao Kobayashi}, title = {Tonal context labeling using quantized F0 symbols for improving tone correctness in average-voice-based speech synthesis}, booktitle = {Proc. 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2011, } @inproceedings{CTT100622330, author = {Takashi Nose and Takao Kobayashi}, title = {Very low bit-rate F0 coding for phonetic vocoder using MSD-HMM with quantized F0 context}, booktitle = {Proc. 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2011, } @inproceedings{CTT100624111, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {日本語話し言葉コーパスを用いた対話音声合成のためのコンテキストの評価}, booktitle = {電子情報通信学会技術研究報告}, year = 2011, } @inproceedings{CTT100619431, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {日本語話し言葉コーパスを用いた対話音声合成のための音韻・韻律コンテキストの検討}, booktitle = {日本音響学会2011年春季研究発表会講演論文集}, year = 2011, } @inproceedings{CTT100619433, author = {前野悠 and 能勢 隆 and 小林隆夫 and 井島勇祐 and 中嶋秀治 and 水野秀之 and 吉岡理}, title = {多様な発話様式によるHMM音声合成のための韻律コンテキストの検討}, booktitle = {日本音響学会2011年春季研究発表会講演論文集}, year = 2011, } @inproceedings{CTT100619434, author = {史潤宇 and 能勢 隆 and 小林隆夫}, title = {合成音声を用いた非パラレルデータによる声質変換の検討}, booktitle = {日本音響学会2011年春季研究発表会講演論文集}, year = 2011, } @inproceedings{CTT100619430, author = {斉藤辰彦 and 能勢 隆 and 小林隆夫 and 岡登洋平}, title = {平均声に基づく音声合成を用いた音声認識性能予測の検討}, booktitle = {日本音響学会2011年春季研究発表会講演論文集}, year = 2011, } @inproceedings{CTT100619432, author = {能勢 隆 and 熊本政真 and 小林隆夫}, title = {極低ビットレートボコーダのためのMSD-HMMに基づくF0符号化の評価}, booktitle = {日本音響学会2011年春季研究発表会講演論文集}, year = 2011, } @inproceedings{CTT100616488, author = {能勢 隆 and 熊本政真 and 小林隆夫}, title = {極低ビットレートボコーダのためのHMMに基づくF0符号化法の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2010, } @inproceedings{CTT100612532, author = {能勢 隆 and 小林隆夫}, title = {話者適応を用いたHMMに基づく不特定話者間声質変換}, booktitle = {日本音響学会2010年秋季研究発表会講演論文集}, year = 2010, } @inproceedings{CTT100612534, author = {横溝秀始 and 能勢 隆 and 小林隆夫}, title = {HMMに基づく英語音声合成の韻律コンテキストの評価}, booktitle = {日本音響学会2010年秋季研究発表会講演論文集}, year = 2010, } @inproceedings{CTT100612537, author = {Takashi Nose and Takao Kobayashi}, title = {HMM-based robust voice conversion using adaptive F0 quantization}, booktitle = {Proc. 7th ISCA Workshop on Speech Synthesis}, year = 2010, } @inproceedings{CTT100612538, author = {Shuji Yokomizo and Takashi Nose and Takao Kobayashi}, title = {Evaluation of prosodic contextual factors for HMM-based speech synthesis}, booktitle = {Proc. 11th Annual Conference of the International Speech Communication Association}, year = 2010, } @inproceedings{CTT100612539, author = {Tomoki Koriyama and Takashi Nose and Takao Kobayashi}, title = {Conversational spontaneous speech synthesis using average voice model}, booktitle = {Proc. 11th Annual Conference of the International Speech Communication Association}, year = 2010, } @inproceedings{CTT100612540, author = {Takashi Nose and Takao Kobayashi}, title = {Speaker-independent HMM-based voice conversion using quantized fundamental frequency}, booktitle = {Proc. 11th Annual Conference of the International Speech Communication Association}, year = 2010, } @inproceedings{CTT100612531, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {二段階モデル適応に基づく対話音声合成の検討}, booktitle = {日本音響学会2010年秋季研究発表会講演論文集}, year = 2010, } @inproceedings{CTT100612533, author = {能勢 隆 and 小林隆夫}, title = {適応F0量子化によるHMM声質変換の品質改善}, booktitle = {日本音響学会2010年秋季研究発表会講演論文集}, year = 2010, } @inproceedings{CTT100601339, author = {大木康次郎 and 能勢 隆 and 小林隆夫}, title = {量子化F0韻律コンテキストを用いたHMM音声合成の評価}, booktitle = {日本音響学会2010年春季研究発表会講演論文集}, year = 2010, } @inproceedings{CTT100601335, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {HMMに基づく対話音声合成のための発話単位の検討}, booktitle = {日本音響学会2010年春季研究発表会講演論文集}, year = 2010, } @inproceedings{CTT100601337, author = {太田悠平 and 能勢 隆 and 小林隆夫}, title = {量子化F0コンテキストを用いたHMMに基づく不特定話者声質変換の検討}, booktitle = {日本音響学会2010年春季研究発表会講演論文集}, year = 2010, } @inproceedings{CTT100601341, author = {横溝秀始 and 能勢 隆 and 小林隆夫}, title = {HMM音声合成における韻律コンテキストの評価}, booktitle = {日本音響学会2010年春季研究発表会講演論文集}, year = 2010, } @inproceedings{CTT100601343, author = {Takashi Nose and Koujirou Ooki and Takao Kobayashi}, title = {HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model}, booktitle = {Proc. 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2010, } @inproceedings{CTT100599791, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {平均声に基づく対話音声合成に関する検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2010, } @inproceedings{CTT100599790, author = {太田悠平 and 能勢 隆 and 小林隆夫}, title = {F0量子化と非パラレル学習に基づく声質変換の評価}, booktitle = {電子情報通信学会技術研究報告}, year = 2010, } @inproceedings{CTT100597381, author = {大木康次郎 and 能勢 隆 and 小林隆夫}, title = {F0量子化に基づく韻律コンテキストを用いたHMM音声合成}, booktitle = {電子情報通信学会技術研究報告}, year = 2009, } @inproceedings{CTT100597383, author = {太田悠平 and 能勢 隆 and 小林隆夫}, title = {F0量子化と非パラレル学習に基づく声質変換の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2009, } @inproceedings{CTT100593516, author = {大木康次郎 and 能勢 隆 and 小林隆夫}, title = {HMM音声合成におけるF0モデルの教師なし学習の検討}, booktitle = {日本音響学会2009年秋季研究発表会講演論文集}, year = 2009, } @inproceedings{CTT100593514, author = {郡山知樹 and 能勢 隆 and 小林隆夫}, title = {HMMに基づく対話音声合成の検討}, booktitle = {日本音響学会2009年秋季研究発表会講演論文集}, year = 2009, } @inproceedings{CTT100593508, author = {Takashi Nose and Junichi Asada and Takao Kobayashi}, title = {HMM-based speaker characteristics emphasis using average voice model}, booktitle = {Proc. 10th Annual Conference of the International Speech Communication Association}, year = 2009, } @inproceedings{CTT100593506, author = {Yusuke Ijima and Takeshi Matsubara and Takashi Nose and Takao Kobayashi}, title = {Speaking style adaptation for spontaneous speech recognition using multiple-regression HMM}, booktitle = {Proc. 10th Annual Conference of the International Speech Communication Association}, year = 2009, } @inproceedings{CTT100593517, author = {太田悠平 and 能勢 隆 and 小林隆夫}, title = {F0量子化と非パラレル学習に基づく声質変換}, booktitle = {日本音響学会2009年秋季研究発表会講演論文集}, year = 2009, } @inproceedings{CTT100593515, author = {能勢 隆 and 松原 健 and 井島勇祐 and 小林隆夫}, title = {重回帰HMMに基づく自然発話音声の発話様式識別}, booktitle = {電子情報通信学会技術研究報告}, year = 2009, } @inproceedings{CTT100593513, author = {Yusuke Ijima and Makoto Tachibana and Takashi Nose and Takao Kobayashi}, title = {Emotional speech recognition based on style estimation and adaptationwith multiple-regression HMM}, booktitle = {Proc. 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2009, } @inproceedings{CTT100572440, author = {花井早紀 and 橘 誠 and 小林隆夫}, title = {テレビ放送音に対する音声と音楽およびその混合音の識別に関する検討}, booktitle = {電子情報通信学会2009年総合大会講演論文集}, year = 2009, } @inproceedings{CTT100572437, author = {松原 健 and 井島勇祐 and 橘 誠 and 能勢 隆 and 小林隆夫}, title = {スタイル推定を用いた自然発話音声の発話様式識別に関する検討}, booktitle = {日本音響学会2009年春季研究発表会講演論文集}, year = 2009, } @inproceedings{CTT100572436, author = {橘 誠 and 河野明文 and 能勢 隆 and 小林隆夫}, title = {平均声と重回帰HSMM を用いた合成音声の多様なスタイル・声質制御の検討}, booktitle = {日本音響学会2009年春季研究発表会講演論文集}, year = 2009, } @inproceedings{CTT100572435, author = {浅田惇一 and 能勢 隆 and 橘 誠 and 小林隆夫}, title = {平均声に基づく音声合成における話者強調の検討}, booktitle = {日本音響学会2009年春季研究発表会講演論文集}, year = 2009, } @inproceedings{CTT100572434, author = {太田悠平 and 能勢 隆 and 小林隆夫}, title = {F0量子化を用いたMSD-HMMに基づく声質変換}, booktitle = {日本音響学会2009年春季研究発表会講演論文集}, year = 2009, } @inproceedings{CTT100572438, author = {井島勇祐 and 橘 誠 and 能勢 隆 and 小林隆夫}, title = {スタイル推定を用いた音声認識における音響モデル学習法の評価}, booktitle = {日本音響学会2009年春季研究発表会講演論文集}, year = 2009, } @inproceedings{CTT100572373, author = {井島勇祐 and 橘 誠 and 能勢 隆 and 小林隆夫}, title = {重回帰HMMに基づくスタイル推定を用いた音声認識における音響モデル学習法}, booktitle = {電子情報通信学会技術研究報告}, year = 2008, } @inproceedings{CTT100572370, author = {井島勇祐 and 橘 誠 and 能勢 隆 and 小林隆夫}, title = {スタイル推定に基づく音響モデルのオンライン適応手法の評価}, booktitle = {日本音響学会2008年秋季研究発表会講演論文集}, year = 2008, } @inproceedings{CTT100572385, author = {Yusuke Ijima and Makoto Tachibana and Takashi Nose and Takao Kobayashi}, title = {An on-line adaptation technique for emotional speech recognition using style estimation with multiple-regression HMM}, booktitle = {Proc. 9th Annual Conference of the International Speech Communication Association}, year = 2008, } @inproceedings{CTT100572384, author = {Takashi Nose and Yoichi Kato and Makoto Tachibana and Takao Kobayashi}, title = {An estimation technique of style expressiveness for emotional speech using model adaptation based on multiple-regression HSMM}, booktitle = {Proc. 9th Annual Conference of the International Speech Communication Association}, year = 2008, } @inproceedings{CTT100572371, author = {河野明文 and 橘 誠 and 能勢 隆 and 小林隆夫}, title = {平均声からの話者適応手法と重回帰HSMMによる合成音声の声質制御の検討}, booktitle = {日本音響学会2008年秋季研究発表会講演論文集}, year = 2008, } @inproceedings{CTT100572372, author = {井島勇祐 and 橘 誠 and 能勢 隆 and 小林隆夫}, title = {スタイル推定に基づく音響モデルのオンライン適応手法}, booktitle = {電子情報通信学会技術研究報告}, year = 2008, } @inproceedings{CTT100572375, author = {橘 誠 and 河野明文 and 能勢 隆 and 小林隆夫}, title = {平均声からの話者適応手法を用いた重回帰HSMMに基づく合成音声の声質制御}, booktitle = {電子情報通信学会技術研究報告}, year = 2008, } @inproceedings{CTT100572383, author = {Makoto Tachibana and Shinsuke Izawa and Takashi Nose and Takao Kobayashi}, title = {Speaker and style adaptation using average voice model for style control in HMM-based speech synthesis}, booktitle = {Proc. 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2008, } @inproceedings{CTT100572381, author = {Suphattharachai Chomphan and Takao Kobayashi}, title = {A context clustering technique for improvement of tone intelligibility of average-voice-based Thai speech synthesis}, booktitle = {IEICE Technical Report}, year = 2008, } @inproceedings{CTT100572364, author = {井澤信介 and 能勢 隆 and 橘 誠 and 小林隆夫}, title = {平均声と話者・スタイル適応に基づく合成音声のスタイル制御の検討}, booktitle = {日本音響学会2008年春季研究発表会講演論文集}, year = 2008, } @inproceedings{CTT100572362, author = {山岸順一 and 能勢 隆 and 全 炳河 and 戸田 智基 and 徳田 恵一 and 小林隆夫}, title = {Blizzard Challenge 2007のための平均声に基づくHMM音声合成システムの評価}, booktitle = {日本音響学会2008年春季研究発表会講演論文集}, year = 2008, } @inproceedings{CTT100572365, author = {加藤陽一 and 能勢 隆 and 橘 誠 and 小林隆夫}, title = {モデル適応に基づく重回帰HSMMによるスタイル推定の検討}, booktitle = {日本音響学会2008年春季研究発表会講演論文集}, year = 2008, } @inproceedings{CTT100572366, author = {後藤達哉 and 能勢 隆 and 小林隆夫}, title = {CSMAPLRに基づく話者適応におけるハイパーパラメータ選択に関する検討}, booktitle = {日本音響学会2008年春季研究発表会講演論文集}, year = 2008, } @inproceedings{CTT100572363, author = {大川高志 and 能勢 隆 and 小林隆夫}, title = {平均声方式に基づく音声合成における決定木構築手法の評価}, booktitle = {日本音響学会2008年春季研究発表会講演論文集}, year = 2008, } @inproceedings{CTT100550510, author = {橘 誠 and 小林隆夫}, title = {平均声モデルを用いる合成音声の話者性とスタイルの同時多様化の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2007, } @inproceedings{CTT100550509, author = {井澤信介 and 橘 誠 and 能勢 隆 and 小林隆夫}, title = {重回帰HSMMに基づく合成音声のスタイル制御のための平均声からの話者適応手法}, booktitle = {電子情報通信学会技術研究報告}, year = 2007, } @inproceedings{CTT100550506, author = {井澤信介 and 能勢 隆 and 橘 誠 and 小林隆夫}, title = {合成音声のスタイル制御における平均声からの話者適応手法の検討}, booktitle = {日本音響学会2007年秋季研究発表会講演論文集}, year = 2007, } @inproceedings{CTT100550505, author = {橘 誠 and 井澤信介 and 小林隆夫}, title = {多様なスタイル音声合成のための話者・スタイル適応の性能評価}, booktitle = {日本音響学会2007年秋季研究発表会講演論文集}, year = 2007, } @inproceedings{CTT100550507, author = {能勢 隆 and 小林隆夫}, title = {HMM音声合成におけるスペクトル正規化に基づく音響モデル学習法の検討}, booktitle = {日本音響学会2007年秋季研究発表会講演論文集}, year = 2007, } @inproceedings{CTT100550513, author = {Suphattharachai Chomphan and Takao Kobayashi}, title = {Design of tree-based context clustering for an HMM-based Thai speech synthesis system}, booktitle = {Proc. 6th ISCA Workshop on Speech Synthesis}, year = 2007, } @inproceedings{CTT100550516, author = {Takashi Nose and Yoichi Kato and Takao Kobayashi}, title = {Style estimation of speech based on multiple regression hidden semi-Markov model}, booktitle = {Proc. 8th Annual Conference of the International Speech Communication Association}, year = 2007, } @inproceedings{CTT100550514, author = {Junichi Yamagishi and Takao Kobayashi and Steve Renals and Simon King and Heiga Zen and Tomoki Toda and Keiichi Tokuda}, title = {Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV}, booktitle = {Proc. 6th ISCA Workshop on Speech Synthesis}, year = 2007, } @inproceedings{CTT100550508, author = {橘 誠 and 川島啓吾 and 小林隆夫}, title = {対話エージェントにおける不明確性を含む動作表現のモデル化の検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2007, } @inproceedings{CTT100550512, author = {Takashi Nose and Yoichi Kato and Takao Kobayashi}, title = {A speaker adaptation technique for MRHSMM-based style control of synthetic speech}, booktitle = {Proc. 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = 2007, } @inproceedings{CTT100550355, author = {井澤信介 and 能勢 隆 and 山岸順一 and 小林隆夫}, title = {合成音声のスタイル制御における話者適応の評価}, booktitle = {日本音響学会2007年春季研究発表会講演論文集}, year = 2007, } @inproceedings{CTT100550356, author = {川島啓吾 and 小林隆夫}, title = {不明確性を含む動作表現のためのモデル構築法の検討}, booktitle = {電子情報通信学会2007年総合大会講演論文集}, year = 2007, } @inproceedings{CTT100550354, author = {加藤陽一 and 河野明文 and 能勢隆 and 小林隆夫}, title = {重回帰HSMMに基づくスタイル推定とスタイル音声合成の検討}, booktitle = {日本音響学会2007年春季研究発表会講演論文集}, year = 2007, } @inproceedings{CTT100550353, author = {橘 誠 and 井澤信介 and 能勢隆 and 小林隆夫}, title = {平均声と話者・スタイル適応を用いたスタイル制御法の検討}, booktitle = {日本音響学会2007年春季研究発表会講演論文集}, year = 2007, } @inproceedings{CTT100550352, author = {大川高志 and 緒方克海 and 山岸順一 and 小林隆夫}, title = {平均声に基づく音声合成における合成音声の品質評価}, booktitle = {日本音響学会2007年春季研究発表会講演論文集}, year = 2007, } @inproceedings{CTT100525439, author = {緒方克海 and 橘 誠 and 山岸順一 and 小林隆夫}, title = {平均声に基づく音声合成における線形変換とMAPに基づく音響モデル学習法}, booktitle = {電子情報通信学会技術研究報告}, year = 2006, } @inproceedings{CTT100526268, author = {井澤信介 and 能勢 隆 and 山岸順一 and 小林隆夫}, title = {合成音声のスタイル制御における話者適応の検討}, booktitle = {日本音響学会2006年秋季研究発表会講演論文集}, year = 2006, } @inproceedings{CTT100526266, author = {橘 誠 and 能勢 隆 and 小林隆夫}, title = {重回帰HSMMを用いた音声のスタイル制御における多様性の検討}, booktitle = {日本音響学会2006年秋季研究発表会講演論文集}, year = 2006, } @inproceedings{CTT100526265, author = {大川高志 and 緒方克海 and 山岸順一 and 小林隆夫}, title = {線形変換とMAPに基づく音響モデル学習法の評価}, booktitle = {日本音響学会2006年秋季研究発表会講演論文集}, year = 2006, } @inproceedings{CTT100526399, author = {Takashi Nose and Junichi Yamagishi and Takao Kobayashi}, title = {A style control technique for speech synthesis using multiple regression HSMM}, booktitle = {Proc. 9th International Conference on Spoken Language Processing}, year = 2006, } @inproceedings{CTT100526396, author = {Makoto Tachibana and Takashi Nose and Junichi Yamagishi and Takao Kobayashi}, title = {A technique for controlling voice quality of synthetic speech using multiple regression HSMM}, booktitle = {Proc. 9th International Conference on Spoken Language Processing}, year = 2006, } @inproceedings{CTT100526262, author = {橘 誠 and 能勢 隆 and 山岸順一 and 小林隆夫}, title = {重回帰HSMMに基づく合成音声の声質制御の検討}, booktitle = {日本音響学会2006年春季研究発表会講演論文集}, year = 2006, } @inproceedings{CTT100526263, author = {能勢 隆 and 山岸順一 and 小林隆夫}, title = {重回帰HSMMに基づく音声の発話様式・感情表現の推定}, booktitle = {日本音響学会2006年春季研究発表会講演論文集}, year = 2006, } @inproceedings{CTT100526260, author = {山岸順一 and 小林隆夫}, title = {HMM音声合成のための話者正規化クラスタリングと話者正規化学習}, booktitle = {日本音響学会2006年春季研究発表会講演論文集}, year = 2006, } @inproceedings{CTT100526264, author = {川島啓吾 and 橘 誠 and 山岸順一 and 小林隆夫}, title = {MSD-HMMを用いた音声のスタイル識別手法の評価}, booktitle = {日本音響学会2006年春季研究発表会講演論文集}, year = 2006, } @inproceedings{CTT100526259, author = {中野雄資 and 緒方克海 and 山岸順一 and 小林隆夫}, title = {平均声に基づく音声合成のための話者適応アルゴリズムの評価}, booktitle = {日本音響学会2006年春季研究発表会講演論文集}, year = 2006, } @inproceedings{CTT100526261, author = {緒方克海 and 中野雄資 and 山岸順一 and 小林隆夫}, title = {HSMM音声合成における話者適応とMAPに基づく音響モデル学習法}, booktitle = {日本音響学会2006年春季研究発表会講演論文集}, year = 2006, } @inproceedings{CTT100526272, author = {能勢 隆 and 山岸順一 and 小林隆夫}, title = {重回帰HSMMを用いた合成音声のスタイル制御}, booktitle = {電子情報通信学会技術研究報告}, year = 2006, } @inproceedings{CTT100541172, author = {川島啓吾 and 橘 誠 and 山岸順一 and 小林隆夫}, title = {MSD-HMMに基づく音声のスタイル識別}, booktitle = {電子情報通信学会技術研究報告}, year = 2005, } @inproceedings{CTT100394653, author = {Takashi Yamazaki and Naotake Niwase and Junichi Yamagishi and Takao Kobayashi}, title = {Human walking motion synthesis based on multiple regression hidden semi-Markov model}, booktitle = {Proc. 2005 International Conference on Cyberworlds}, year = 2005, } @inproceedings{CTT100394644, author = {磯貝朱里 and 山岸順一 and 小林隆夫}, title = {HMM音声合成におけるESATアルゴリズムの評価}, booktitle = {日本音響学会2005年秋季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100408963, author = {中野雄資 and 緒方克海 and 磯貝朱里 and 山岸順一 and 小林隆夫}, title = {平均声に基づく音声合成のための話者適応アルゴリズムの検討}, booktitle = {日本音響学会2005年秋季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100394643, author = {山岸順一 and 河井 恒 and 小林隆夫}, title = {Naive Markov Modelによるポーズ予測アルゴリズム}, booktitle = {日本音響学会2005年秋季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100394642, author = {能勢 隆 and 山岸順一 and 小林隆夫}, title = {重回帰HSMMを用いた音声のスタイル制御法の検討}, booktitle = {日本音響学会2005年秋季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100394641, author = {小林隆夫}, title = {多様な話者性および発話スタイル・感情表現による音声合成}, booktitle = {日本音響学会2005年秋季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100394651, author = {橘 誠 and 山岸順一 and 小林隆夫}, title = {多様な音声合成のためのスタイル適応アルゴリズムの比較検討}, booktitle = {日本音響学会2005年秋季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100502311, author = {川島啓吾 and 山岸順一 and 小林隆夫}, title = {MSD-HMMを用いた音声のスタイル識別の検討}, booktitle = {日本音響学会2005年秋季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100394640, author = {中野雄資 and 緒方克海 and 磯貝朱里 and 山岸順一 and 小林隆夫}, title = {平均声に基づく音声合成のための話者適応アルゴリズムの検討}, booktitle = {日本音響学会2005年秋季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100394638, author = {磯貝朱里 and 緒方克海 and 中野雄資 and 山岸順一 and 小林隆夫}, title = {多様な音声合成のためのモデル適応・適応学習アルゴリズムの検討}, booktitle = {電子情報通信学会技術研究報告}, year = 2005, } @inproceedings{CTT100394637, author = {橘 誠 and 山岸順一 and 小林隆夫}, title = {隠れセミマルコフモデルに基づく音声合成システムのためのスタイル適応手法の評価}, booktitle = {電子情報通信学会技術研究報告}, year = 2005, } @inproceedings{CTT100540823, author = {山岸順一 and 河井 恒 and 平井俊男 and 小林隆夫}, title = {アンサンブル学習に基づく音韻継続長のモデル化}, booktitle = {電子情報通信学会技術研究報告}, year = 2005, } @inproceedings{CTT100394647, author = {橘 誠 and 山岸順一 and 益子貴史 and 小林隆夫}, title = {モデル補間による発話スタイル・感情表現の制御の検討}, booktitle = {日本音響学会2005年春季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100394649, author = {古宮弘智 and 庭瀬尚武 and 小林隆夫}, title = {あいまい表現入力が可能な音声対話エージェントシステムの検討}, booktitle = {電子情報通信学会2005年総合大会講演論文集}, year = 2005, } @inproceedings{CTT100394650, author = {庭瀬尚武 and 山岸順一 and 小林隆夫}, title = {歩行速度とテンポを考慮した歩行動作の生成}, booktitle = {電子情報通信学会2005年総合大会講演論文集}, year = 2005, } @inproceedings{CTT100394645, author = {磯貝朱里 and 山岸順一 and 小林隆夫}, title = {HMM音声合成におけるESATアルゴリズムを用いたモデル適応および適応学習の検討}, booktitle = {日本音響学会2005年春季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100394646, author = {山岸順一 and 小林隆夫}, title = {隠れセミマルコフモデルに基づく適応学習アルゴリズム}, booktitle = {日本音響学会2005年春季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100394648, author = {野村大輔 and 山岸順一 and 小林隆夫}, title = {HMM音声合成における決定木の分割停止基準の検討}, booktitle = {日本音響学会2005年春季研究発表会講演論文集}, year = 2005, } @inproceedings{CTT100502310, author = {山岸順一 and 益子貴史 and 小林隆夫}, title = {隠れセミマルコフモデルに基づく最尤線形回帰の検討}, booktitle = {日本音響学会2004年秋季研究発表会講演論文集}, year = 2004, } @misc{CTT100715039, author = {小林隆夫}, title = {音声合成技術}, year = 2015, } @misc{CTT100616784, author = {小林隆夫}, title = {小特集―音声合成に関する研究の動向―小特集にあたって}, year = 2011, } @misc{CTT100801116, author = {Takao Kobayashi}, title = {Special section on processing natural speech variability for improved verbal human-computer interaction}, year = 2010, } @misc{CTT100408962, author = {小林隆夫 and 徳田恵一}, title = {コーパスベース音声合成技術の動向[IV] － HMM音声合成方式 －}, year = 2004, } @misc{CTT100596389, author = {小林隆夫}, title = {一般化ケプストラムを用いる音声の分析・合成と合成フィルタの特性近似}, year = 1982, } @misc{CTT100845910, author = {小林隆夫 and 郡山知樹 and 井島 勇祐}, title = {学習装置、推定装置、推定方法、およびプログラム}, howpublished = {登録特許}, year = 2022, month = {}, note = {特願2019-127181(2019/07/08), 特開2021-012315(2021/02/04), 特許第7093081号(2022/06/21)} } @misc{CTT100669100, author = {小林隆夫 and 能勢隆 and 前野　悠 and 水野　秀之 and 井島　勇祐 and 中嶋　秀治 and 吉岡　理}, title = {局所韻律コンテキスト付与装置、局所韻律コンテキスト付与方法、およびプログラム}, howpublished = {登録特許}, year = 2016, month = {}, note = {特願2012-258302(2012/11/27), 特開2013-242515(2013/12/05), 特許第5967578号(2016/07/15)} } @misc{CTT100573391, author = {小林隆夫 and 山岸　順一 and 能勢　隆}, title = {音声のスタイル検出装置、その方法およびそのプログラム}, howpublished = {公開特許}, year = 2007, month = {}, note = {特願2006-041172(2006/02/17), 特開2007-219286(2007/08/30)} } @phdthesis{CTT100596389, author = {小林隆夫}, title = {一般化ケプストラムを用いる音声の分析・合成と合成フィルタの特性近似}, school = {東京工業大学}, year = 1982, }