"Tomoki Koriyama,Shinnosuke Takamichi,Takao Kobayashi","Sparse Approximation of Gram Matrices for GMMN-based Speech Synthesis","The 10th ISCA Speech Synthesis Workshop (SSW)","Proc. SSW10","ISCA",,,"pp. 149-154",2019,Sept.
"Tomoki Koriyama,Takao Kobayashi","Semi-supervised prosody modeling using deep Gaussian process latent variable model","Interspeech 2019","Proc. 20th Annual Conference of the International Speech Communication (INTERSPEECH 2019)","ISCA",,,"pp. 4450-4454",2019,Sept.
"蛭田宜樹,郡山知樹,小林隆夫","DNN音声合成におけるスタイル付与モデル学習法の検討",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 119","No. 80","pp. 1-6",2019,June
"Tomoki Koriyama,Takao Kobayashi","A training method using DNN-guided layerwise pretraining for deep Gaussian processes","ICASSP 2017","Proc. 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019)","IEEE",,,"pp. 2787-2791",2019,May
"Tomoki Koriyama,Takao Kobayashi","Statistical parametric speech synthesis using deep Gaussian processes",,"IEEE/ACM Transaction on Audio, Speech, and Language Processing","The Institute of Electrical and Electronics Engineers","Vol. 27","No. 5","pp. 948-959",2019,May
"蛭田宜樹,郡山知樹,太刀岡勇気,小林隆夫","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","日本音響学会2019年春季研究発表会","日本音響学会2019年春季研究発表会講演論文集","日本音響学会",,,"pp. 1119-1120",2019,Mar.
"郡山知樹,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 118","No. 497","pp. 179-184",2019,Mar.
"郡山知樹,高道慎之介,小林隆夫","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","日本音響学会2019年春季研究発表会","日本音響学会2019年春季研究発表会講演論文集","日本音響学会",,,"pp. 1065-1068",2019,Mar.
"成田昂世,郡山知樹,小林隆夫,井島勇祐","対話情報を考慮した韻律生成の検討","日本音響学会2019年春季研究発表会","日本音響学会2019年春季研究発表会講演論文集","日本音響学会",,,"pp. 1131-1132",2019,Mar.
"郡山知樹,高道慎之介,小林隆夫","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",,"情報処理学会研究報告","情報処理学会","Vol. 2019-SLP-126","No. 1","pp. 1-6",2019,Feb.
"郡山知樹,小林隆夫","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","日本音響学会2018年秋季研究発表会","日本音響学会2018年秋季研究発表会講演論文集","日本音響学会",,,"pp. 1089-1090",2018,Sept.
"蛭田宜樹,郡山知樹,小林隆夫","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","日本音響学会2018年秋季研究発表会","日本音響学会2018年秋季研究発表会講演論文集","日本音響学会",,,"pp. 1169-1170",2018,Sept.
"Decha Moungsri,Tomoki Koriyama,Takao Kobayashi","GPR-based Thai speech synthesis using multi-level duration prediction",,"Speech Communication","Elsevier","Vol. 99",,"pp. 114-123",2018,May
"郡山知樹,小林隆夫","GPR音声合成における深層ガウス過程の利用の検討",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 117","No. 517","pp. 27-32",2018,Mar.
"郡山知樹,小林隆夫","GPR音声合成における深層構造の利用の検討","日本音響学会2018年春季研究発表会","日本音響学会2018年春季研究発表会講演論文集","日本音響学会",,,"pp. 1507-1508",2018,Mar.
"前野雄也,郡山知樹,小林隆夫","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","日本音響学会2018年春季研究発表会","日本音響学会2018年春季研究発表会講演論文集","日本音響学会",,,"pp. 295-296",2018,Mar.
"郡山知樹,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 117","No. 393","pp. 5-10",2018,Jan.
"Nattapong Kurpukdee,Tomoki Koriyama,Takao Kobayashi,Sawit Kasuriya,Chai Wutiwiwatchai,Poonlap Lamsrichan","Speech emotion recognition using convolutional long short-term memory neural network and support vector machines","APSIPA ASC 2017","Proc. 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","APSIPA",,,,2017,Dec.
"Decha Moungsri,Tomoki Koriyama,Takao Kobayashi","Enhanced F0 generation for GPR-based speech synthesis considering syllable-based prosodic features","APSIPA ASC 2017","Proc. 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","APSIPA",,,,2017,Dec.
"小林隆夫","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","第19回音声言語シンポジウム","電子情報通信学会技術研究報告","電子情報通信学会","Vol. 117","No. 368","pp. 85-86",2017,Dec.
"郡山知樹,岡野 祐紀,小林隆夫","ガウス過程回帰に基づく歌声合成の検討","日本音響学会2017年秋季研究発表会","日本音響学会2017年秋季研究発表会講演論文集","日本音響学会",,,"pp. 295-296",2017,Sept.
"郡山知樹,小林隆夫","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","日本音響学会2017年秋季研究発表会","日本音響学会2017年秋季研究発表会講演論文集","日本音響学会",,,"pp. 177-178",2017,Sept.
"Takashi Nose,Yusuke Arao,Takao Kobayashi,Komei Sugiura,Yoshinori Shiga","Sentence selection based on extended entropy using phonetic and prosodic contexts for statistical paramaetric speech synthesis",,"IEEE/ACM Transaction on Audio, Speech, and Language Processing","The Institute of Electrical and Electronics Engineers","Vol. 25","No. 5","pp. 1107-1116",2017,May
"津野駿幸,郡山知樹,小林隆夫","GPR音声合成に基づいたオーディオブック音声の合成","日本音響学会2017年春季研究発表会","日本音響学会2017年春季研究発表会講演論文集","日本音響学会",,,"pp. 295-296",2017,Mar.
"長濱大樹,能勢 隆,郡山知樹,小林隆夫","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",,"電子情報通信学会論文誌D","電子情報通信学会","Vol. J100-D","No. 3","pp. 385-393",2017,Mar.
"Decha Moungsri,Tomoki Koriyama,Takao Kobayashi","Duration Prediction Using Multiple Gaussian Process Experts For GPR-based Speech Synthesis","ICASSP 2017","Proc. 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017)","IEEE",,,"pp. 5495-5498",2017,Mar.
"増子理菜,郡山知樹,小林隆夫","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","日本音響学会2017年春季研究発表会","日本音響学会2017年春季研究発表会講演論文集","日本音響学会",,,"pp. 283-284",2017,Mar.
"高橋亮,郡山知樹,小林隆夫","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","日本音響学会2017年春季研究発表会","日本音響学会2017年春季研究発表会講演論文集","日本音響学会",,,"pp. 367-378",2017,Mar.
"高橋亮,郡山知樹,小林隆夫","非パラレルデータを用いるGMM声質変換の検討","日本音響学会2016年秋季研究発表会","日本音響学会2016年秋季研究発表会講演論文集","日本音響学会",,,"pp. 267-268",2016,Sept.
"Decha Moungsri,Tomoki Koriyama,Takao Kobayashi","Unsupervised Stress Information Labeling Using Gaussian Process Latent Variable Model for Statistical Speech Synthesis","Interspeech 2016","Proc. 17th Annual Conference of the International Speech Communication (INTERSPEECH 2016)","ISCA",,,"pp. 1517-1521",2016,Sept.
"前野雄也,押尾翔平,郡山知樹,小林隆夫","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","日本音響学会2016年秋季研究発表会","日本音響学会2016年秋季研究発表会講演論文集","日本音響学会",,,"pp. 213-214",2016,Sept.
"Decha Moungsri,Tomoki Koriyama,Takao Kobayashi","Tone modeling using Gaussian process latent variable model for statistical speech synthesis","Speech Prosody 2016","Proc. Speech Prosody 2016","ISCA",,,"pp. 1014-1018",2016,May
"前野雄也,郡山知樹,小林隆夫","GPR音声合成におけるスタイル適応の検討","日本音響学会2016年春季研究発表会","日本音響学会2016年春季研究発表会講演論文集","日本音響学会",,,"pp. 233-234",2016,Mar.
"Tomoki Koriyama,Syohei Oshio,Takao Kobayashi","A Speaker Adaptation Technique For Gaussian Process Regression Based Speech Synthesis Using Feature Space Transform","ICASSP 2016","Proc. 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016)","IEEE",,,"pp. 5610-5614",2016,Mar.
"岡元伶洋,郡山知樹,小林隆夫","多様なスタイルによるGPR音声合成の検討","日本音響学会2016年春季研究発表会","日本音響学会2016年春季研究発表会講演論文集","日本音響学会",,,"pp. 358-359",2016,Mar.
"増子理菜,郡山知樹,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 115","No. 392","pp. 1-6",2016,Jan.
"Takashi Nose,Misa Kanemoto,Tomoki Koriyama,Takao Kobayashi","HMM-based expressive singing voice synthesis with singing style control and robust pitch modeling",,"Computer Speech & Language","Elsevier","Vol. 34","No. 1","pp. 308-322",2015,Nov.
"Tomoki Koriyama,Takao Kobayashi","A comparison of speech synthesis systems based on GPR, HMM, and DNN with a small amount of training data","INTERSPEECH 2015","Proc. 16th Annual Conference of the International Speech Communication","ISCA",,,"pp. 3496-3500",2015,Sept.
"Takashi Nose,Yusuke Arao,Takao Kobayashi,Komei Sugiura,Yoshinori Shiga,Akinori Ito","Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts","INTERSPEECH 2015","Proc. 16th Annual Conference of the International Speech Communication","ISCA",,,"pp. 3491-3495",2015,Sept.
"押尾翔平,郡山知樹,小林隆夫","GPR音声合成における話者適応手法の検討","日本音響学会2015年秋季研究発表会","日本音響学会2015年秋季研究発表会講演論文集","日本音響学会",,,"pp. 219-220",2015,Sept.
"郡山知樹,小林隆夫","ガウス過程回帰に基づく音声合成システムの評価","日本音響学会2015年秋季研究発表会","日本音響学会2015年秋季研究発表会講演論文集","日本音響学会",,,"pp. 235-236",2015,Sept.
"Decha Moungsri,Tomoki Koriyama,Takao Kobayashi","Duration prediction using multi-level model for GPR-based speech synthesis","INTERSPEECH 2015","Proc. 16th Annual Conference of the International Speech Communication","ISCA",,,"pp. 1591-1595",2015,Sept.
"小林隆夫","音声合成技術",,"電子情報通信学会誌","電子情報通信学会","Vol. 98","No. 8","pp. 726-733",2015,Aug.
"能勢 隆,荒生 侑介,小林 隆夫,杉浦 孔明,志賀 芳則","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","音声研究会","電子情報通信学会技術研究報告","電子情報通信学会","Vol. 115","No. 184","pp. 39-44",2015,Aug.
"Tomoki Koriyama,Takao Kobayashi","Prosody Generation Using Frame-based Gaussian Process Regression and Classification for Statistical Parametric Speech Synthesis","ICASSP 2015","Proc. ICASSP 2015","IEEE",,,"pp. 4929-4933",2015,Apr.
"岡元伶洋,郡山知樹,小林隆夫","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","日本音響学会2015年春季研究発表会","日本音響学会2015年春季研究発表会講演論文集","日本音響学会",,,"pp. 371-372",2015,Mar.
"増子 理菜,郡山 知樹,篠崎 隆宏,小林 隆夫","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","日本音響学会2015年春季研究発表会","日本音響学会2015年春季研究発表会講演論文集","日本音響学会",,,"pp. 361-362",2015,Mar.
"郡山知樹,小林隆夫","ガウス過程回帰に基づく音声合成システムの検討","日本音響学会2015年春季研究発表会","日本音響学会2015年春季研究発表会講演論文集","日本音響学会",,,"pp. 269-270",2015,Mar.
"Takao Kobayashi","Prosody Control and Variation Enhancement Techniques for HMM-Based Expressive Speech Synthesis",,"Speech Prosody in Speech Synthesis: Modeling and generation of prosody for high quality and flexible speech synthesis","Springer",,,"pp. 203-213",2015,Feb.
"Decha Moungsri,Tomoki Koriyama,Takao Kobayashi","HMM-based Thai speech synthesis using unsupervised stress context labeling","APSIPA ASC 2014","Proc. 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","APSIPA",,,,2014,Dec.
"Daiki Nagahama,Takashi Nose,Tomoki Koriyama,Takao Kobayashi","Transform mapping using shared decision tree context clustering for HMM-based cross-lingual speech synthesis","INTERSPEECH 2014","Proc. INTERSPEECH 2014","ISCA",,,"pp. 770-774",2014,Sept.
"Tomoki Koriyama,Hiroshi Suzuki,Takashi Nose,Takahiro Shinozaki,Takao Kobayashi","Accent Type and Phrase Boundary Estimation Using Acoustic and Language Models for Automatic Prosodic Labeling","INTERSPEECH 2014","Proc. INTERSPEECH 2014","ISCA",,,"pp. 2337-2341",2014,Sept.
"Tomoki Koriyama,Takashi Nose,Takao Kobayashi","Parametric Speech Synthesis Using Local and Global Sparse Gaussian Processes","MLSP 2014","Proc. The 24th IEEE International Workshop on Machine Learning for Signal Processing","IEEE",,,,2014,Sept.
"荒生 侑介,能勢 隆,篠崎 隆宏,小林 隆夫","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","日本音響学会","秋季講演論文集",,,,"pp. 351 - 352",2014,Sept.
"小林 友哉,能勢 隆,篠崎 隆宏,小林 隆夫","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","日本音響学会","秋季講演論文集",,,,"pp. 341-342",2014,Sept.
"房 福明,篠崎隆宏,小林隆夫","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","日本音響学会","秋季研究発表会講演論文集",,,,"pp. 229-230",2014,Sept.
"博多屋 涼,篠崎隆宏,小林隆夫","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","日本音響学会","秋季研究発表会講演論文集",,,,"pp. 59-60",2014,Sept.
"小林 隆夫,高木 茂孝","ディジタル集積回路入門",,"ディジタル集積回路入門","朝倉書店",,,,2014,Sept.
"郡山知樹,能勢 隆,小林隆夫","ガウス過程回帰に基づくF0パタン生成の検討","日本音響学会2014年秋期研究発表会","日本音響学会2014年秋期研究発表会講演論文集","日本音響学会",,,,2014,Sept.
"Decha Moungsri,Tomoki Koriyama,Takashi Nose,Takao Kobayashi","Tone Modeling Using Stress Information for HMM-Based Thai Speech Synthesis","Speech Prosody 2014","Proc. Speech Prosody 2014","ISCA",,,"pp. 1057-1061",2014,May
"Tomoki Koriyama,Takashi Nose,Takao Kobayashi","Parametric Speech Synthesis Based on Gaussian Process Regression Using Global Variance and Hyperparameter Optimization","ICASSP 2014","Proc. ICASSP 2014","IEEE",,,"pp. 3862-3866",2014,May
"房福明,篠崎 隆宏,小林隆夫","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",,"電子情報通信学会技術研究報告 = IEICE technical report : 信学技報","一般社団法人電子情報通信学会","Vol. 114","No. 52","pp. 355-360",2014,May
"Tomoki Koriyama,Takashi Nose,Takao Kobayashi","Statistical Parametric Speech Synthesis Based on Gaussian Process Regression",,"IEEE Journal of Selected Topics in Signal Processing",,"Vol. 8","No. 2","pp. 173-183",2014,Apr.
"Takashi Nose,Vataya Chunwijitra,Takao Kobayashi","A Parameter Generation Algorithm Using Local Variance for HMM-Based Speech Synthesis",,"IEEE Journal of Selected Topics in Signal Processing","IEEE","Vol. 8","No. 2","pp. 221-228",2014,Apr.
"鈴木啓史,郡山知樹,能勢 隆,篠崎隆宏,小林隆夫","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","日本音響学会2014年春季研究発表会","日本音響学会2014年春季研究発表会講演論文集","日本音響学会",,,"pp. 441-442",2014,Mar.
"長濱大樹,能勢 隆,郡山知樹,小林隆夫","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","日本音響学会2014年春季研究発表会","日本音響学会2014年春季研究発表会講演論文集","日本音響学会",,,"pp. 413-414",2014,Mar.
"大西浩之,能勢 隆,郡山知樹,小林隆夫","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","日本音響学会2014年春季研究発表会","日本音響学会2014年春季研究発表会講演論文集","日本音響学会",,,"pp. 411-412",2014,Mar.
"舘野英樹,能勢 隆,郡山知樹,篠崎隆宏,小林隆夫","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","日本音響学会2014年春季研究発表会","日本音響学会2014年春季研究発表会講演論文集","日本音響学会",,,"pp. 409-410",2014,Mar.
"荒生侑介,能勢 隆,郡山知樹,篠崎隆宏,小林隆夫","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","日本音響学会2014年春季研究発表会","日本音響学会2014年春季研究発表会講演論文集","日本音響学会",,,"pp. 405-406",2014,Mar.
"郡山知樹,能勢 隆,小林隆夫","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","日本音響学会2014年春季研究発表会","日本音響学会2014年春季研究発表会講演論文集","日本音響学会",,,"pp. 355-356",2014,Mar.
"Yu Maeno,Takashi Nose,Takao Kobayashi,Tomoki Koriyama,Yusuke Ijima,Hideharu Nakajima,Hideyuki Mizuno,Osamu Yoshioka","Prosodic Variation Enhancement Using Unsupervised Context Labeling for HMM-based Expressive Speech Synthesis",,"Speech Communication","Elsevier","Vol. 57","No. 3","pp. 144-154",2014,Feb.
"郡山知樹,能勢 隆,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 113","No. 404","pp. 19-24",2014,Jan.
"Nose, T.,Takao Kobayashi","Quantized f0 context and its applications to speech synthesis, speech coding, and voice conversion",,"Proceedings - 2014 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2014",,,,"pp. 578-581",2014,
"Fang, F.,Takahiro Shinozaki,Takao Kobayashi","An automatic input protocol recommendation method for tailored switch-to-speech communication aid systems",,"2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2014",,,,,2014,
"鈴木啓史,郡山知樹,能勢 隆,篠崎隆宏,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 113","No. 366","pp. 97-102",2013,Dec.
"小林隆夫","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)",,"電子情報通信学会技術研究報告. SP, 音声","一般社団法人電子情報通信学会","Vol. 113","No. 366","pp. 119-122",2013,Dec.
"小林隆夫","多様な音声合成に向けた取組みと課題",,"研究報告音声言語情報処理（SLP）","一般社団法人情報処理学会","Vol. 2013","No. 20","pp. 1-4",2013,Dec.
"鈴木 啓史,郡山 智樹,能勢 隆,篠崎 隆宏,小林隆夫","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",,"研究報告音声言語情報処理（SLP）","一般社団法人情報処理学会","Vol. 2013","No. 16","pp. 1-6",2013,Dec.
"郡山知樹,能勢 隆,小林隆夫","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","日本音響学会2013年秋期研究発表会","日本音響学会2013年秋期研究発表会講演論文集","日本音響学会",,,"pp. 311-312",2013,Sept.
"Tomoki Koriyama,Takashi Nose,Takao Kobayashi","Statistical nonparametric speech synthesis using sparse Gaussian processes","INTERSPEECH 2013","Proc. INTERSPEECH 2013","ISCA",,,"pp. 1072-1076",2013,Aug.
"Takashi Nose,Misa Kanemoto,Tomoki Koriyama,Takao Kobayashi","A Style Control Technique for Singing Voice Synthesis Based on Multiple-regression HSMM","INTERSPEECH 2013","Proc. INTERSPEECH 2013","ISCA",,,"pp. 378-382",2013,Aug.
"Hiroki Kanagawa,Takashi Nose,Takao Kobayashi","Speaker-independent style conversion for HMM-based expressive speech synthesis","ICASSP 2013","Proc. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing",,,,"pp. 7864-7867",2013,May
"Yu Maeno,Takashi Nose,Takao Kobayashi,Tomoki Koriyama,Yusuke Ijima,Hideharu Nakajima,Hideyuki Mizuno,Osamu Yoshioka","HMM-based expressive speech synthesis based on phrase-level F0 context labeling","ICASSP 2013","Proc. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing",,,,"pp. 7859-7863",2013,May
"Tomoki Koriyama,Takashi Nose,Takao Kobayashi","Frame-level acoustic modeling based on Gaussian process regression for statistical nonparametric speech synthesis","ICASSP 2013","Proc. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing",,,,"pp. 8007-8010",2013,May
"荒生侑介,能勢 隆,小林隆夫","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","日本音響学会2013年春季研究発表会","日本音響学会2013年春季研究発表会講演論文集","日本音響学会",,,"pp. 499-500",2013,Mar.
"金川裕紀,能勢 隆,小林隆夫","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","日本音響学会2013年春季研究発表会","日本音響学会2013年春季研究発表会講演論文集","日本音響学会",,,"pp. 295-296",2013,Mar.
"郡山知樹,能勢 隆,小林隆夫","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","日本音響学会2013年春季研究発表会","日本音響学会2013年春季研究発表会講演論文集","日本音響学会",,,"pp. 271-272",2013,Mar.
"Takashi Nose,Takao Kobayashi","An intuitive style control technique in HMM-based expressive speech synthesis using subjective style intensity and multiple-regression global variance model",,"Speech Communication","Elsevier","Vol. 55","No. 2","pp. 347-357",2013,Feb.
"前野 悠,能勢 隆,小林隆夫,郡山知樹,井島勇祐,中嶋秀治,水野秀之,吉岡 理","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 112","No. 422","pp. 85-90",2013,Jan.
"能勢 隆,金本美沙,郡山知樹,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 112","No. 422","pp. 79-84",2013,Jan.
"金川裕紀,能勢 隆,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 112","No. 422","pp. 73-78",2013,Jan.
"能勢 隆,CHUNWIJITRA VATAYA,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 112","No. 81","pp. 43-48",2012,Nov.
"金川裕紀,能勢 隆,小林隆夫","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","日本音響学会2012年秋季研究発表会","日本音響学会2012年秋季研究発表会講演論文集","日本音響学会",,,"pp. 431-432",2012,Sept.
"能勢 隆,小林隆夫","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","日本音響学会2012年秋季研究発表会","日本音響学会2012年秋季研究発表会講演論文集","日本音響学会",,,"pp. 279-280",2012,Sept.
"能勢 隆,ワータヤー・チュンウィジター,小林隆夫","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","日本音響学会2012年秋季研究発表会","日本音響学会2012年秋季研究発表会講演論文集","日本音響学会",,,"pp. 277-278",2012,Sept.
"Vataya Chunwijitra,Takashi Nose,Takao Kobayashi","A speech parameter generation algorithm using local variance for HMM-based speech synthesis","INTERSPEECH 2012","Proc. 13th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,,2012,Sept.
"Tomoki Koriyama,Takashi Nose,Takao Kobayashi","Discontinuous observation HMM for prosodic-event-based F0 generation","INTERSPEECH 2012","Proc. 13th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 462-465",2012,Sept.
"前野 悠,能勢 隆,小林 隆夫,井島 勇祐,中嶋 秀治,水野 秀之,吉岡 理","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 112","No. 81","pp. 1-6",2012,June
"郡山知樹,能勢 隆,小林 隆夫","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",,"電子情報通信学会論文誌","電子情報通信学会","Vol. J95-D","No. 3","pp. 597-607",2012,Mar.
"Takashi Nose,Takao Kobayashi","Very low bit-rate F0 coding for phonetic vocoders using MSD-HMM with quantized F0 symbols",,"Speech Communication","Elsevier","Vol. 54","No. 3","pp. 384-392",2012,Mar.
"郡山 知樹,能勢 隆,小林隆夫","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","日本音響学会2012年春季研究発表会","日本音響学会2012年春季研究発表会講演論文集","日本音響学会",,,"pp. 305-306",2012,Mar.
"能勢 隆,小林隆夫","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","日本音響学会2012年春季研究発表会","日本音響学会2012年春季研究発表会講演論文集","日本音響学会",,,"pp. 307-308",2012,Mar.
"Tomoki Koriyama,Takashi Nose,Takao Kobayashi","An F0 modeling technique based on prosodic events for spontaneous speech synthesis","ICASSP 2012","Proc. 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing",,,,"pp. 4589-4592",2012,Mar.
"Vataya Chunwijitra,Takashi Nose,Takao Kobayashi","A tone-modeling technique using a quantized F0 context to improve tone correctness in average-voice-based speech synthesis",,"Speech Communication","Elsevier","Vol. 54","No. 2","pp. 245-255",2012,Feb.
"能勢 隆,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 111","No. 365","pp. 197-202",2011,Dec.
"郡山知樹,能勢 隆,小林隆夫","韻律イベントHMMを用いた対話音声F0生成",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 111","No. 365","pp. 185-190",2011,Dec.
"金川裕紀,能勢 隆,小林隆夫","HMM音声合成における不特定話者スタイル変換の検討",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 111","No. 365","pp. 191-196",2011,Dec.
"Takashi Nose,Takao Kobayashi","Recent development of HMM-based expressive speech synthesis and its applications","2011 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2011)","Proc. 2011 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2011)",,,,"  PID:189",2011,Oct.
"太刀岡 勇気,堀井 昭男,岩崎 知弘,斉藤 辰彦,能勢 隆,小林隆夫","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 −","日本音響学会2011年秋季研究発表会","日本音響学会2011年秋季研究発表会講演論文集","日本音響学会",,,"pp. 9-10",2011,Sept.
"Takashi Nose,Takao Kobayashi","Speaker-independent HMM-based voice conversion using adaptive quantization of the fundamental frequency",,"Speech Communication","Elsevier","Vol. 53","No. 7","pp. 973-985",2011,Sept.
"郡山 知樹,能勢 隆,小林隆夫","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","日本音響学会2011年秋季研究発表会","日本音響学会2011年秋季研究発表会講演論文集","日本音響学会",,,"pp. 333-334",2011,Sept.
"能勢 隆,小林隆夫","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","日本音響学会2011年秋季研究発表会","日本音響学会2011年秋季研究発表会講演論文集","日本音響学会",,,"pp. 329-330",2011,Sept.
"前野 悠,能勢 隆,小林隆夫,井島 勇祐,中嶋 秀治,水野 秀之,吉岡 理","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","日本音響学会2011年秋季研究発表会","日本音響学会2011年秋季研究発表会講演論文集","日本音響学会",,,"pp. 335-336",2011,Sept.
"Tomoki Koriyama,Takashi Nose,Takao Kobayashi","On the use of extended context for HMM-based spontaneous conversational speech synthesis","INTERSPEECH 2011","Proc. 12th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 2657-2660",2011,Aug.
"Tatsuhiko Saito,Takashi Nose,Takao Kobayashi,Yohei Okato,Akio Horii","Performance prediction of speech recognition using average-voice-based speech synthesis","INTERSPEECH 2011","Proc. 12th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 1953-1956",2011,Aug.
"Yu Maeno,Takashi Nose,Takao Kobayashi,Yusuke Ijima,Hideharu Nakajima,Hideyuki Mizuno,Osamu Yoshioka","HMM-based emphatic speech synthesis using unsupervised context labeling","INTERSPEECH 2011","Proc. 12th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 1849-1852",2011,Aug.
"Takashi Nose,Takao Kobayashi","A perceptual expressivity modeling technique for speech synthesis based on multiple-regression HSMM","INTERSPEECH 2011","Proc. 12th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 109-112",2011,Aug.
"Takashi Nose,Takao Kobayashi","Very low bit-rate F0 coding for phonetic vocoder using MSD-HMM with quantized F0 context","ICASSP 2011","Proc. 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing",,,,"pp. 5236-5239",2011,May
"郡山知樹,能勢 隆,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 111","No. 28","pp. SP2011-27, 155-160",2011,May
"Vataya Chunwijitra,Takashi Nose,Takao Kobayashi","Tonal context labeling using quantized F0 symbols for improving tone correctness in average-voice-based speech synthesis","ICASSP 2011","Proc. 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing",,,,"pp. 4708-4711",2011,May
"史潤宇,能勢 隆,小林隆夫","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","日本音響学会2011年春季研究発表会","日本音響学会2011年春季研究発表会講演論文集","日本音響学会",,,"pp. 411-412",2011,Mar.
"斉藤辰彦,能勢 隆,小林隆夫,岡登洋平","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","日本音響学会2011年春季研究発表会","日本音響学会2011年春季研究発表会講演論文集","日本音響学会",,,"pp. 149-150",2011,Mar.
"郡山知樹,能勢 隆,小林隆夫","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","日本音響学会2011年春季研究発表会","日本音響学会2011年春季研究発表会講演論文集","日本音響学会",,,"pp. 297-298",2011,Mar.
"能勢 隆,熊本政真,小林隆夫","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","日本音響学会2011年春季研究発表会","日本音響学会2011年春季研究発表会講演論文集","日本音響学会",,,"pp. 335-336",2011,Mar.
"前野悠,能勢 隆,小林隆夫,井島勇祐,中嶋秀治,水野秀之,吉岡理","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","日本音響学会2011年春季研究発表会","日本音響学会2011年春季研究発表会講演論文集","日本音響学会",,,"pp. 385-386",2011,Mar.
"小林隆夫","小特集―音声合成に関する研究の動向―小特集にあたって",,"日本音響学会誌","日本音響学会","Vol. 67","No. 1","pp. 15-16",2011,Jan.
"能勢 隆,熊本政真,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 110","No. 357","pp. SP2010-101, 189-194",2010,Dec.
"Tomoki Koriyama,Takashi Nose,Takao Kobayashi","Conversational spontaneous speech synthesis using average voice model","INTERSPEECH 2010","Proc. 11th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 853-856",2010,Sept.
"Takashi Nose,Takao Kobayashi","Speaker-independent HMM-based voice conversion using quantized fundamental frequency","INTERSPEECH 2010","Proc. 11th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 1724-1727",2010,Sept.
"郡山知樹,能勢 隆,小林隆夫","二段階モデル適応に基づく対話音声合成の検討","日本音響学会2010年秋季研究発表会","日本音響学会2010年秋季研究発表会講演論文集","日本音響学会",,,"pp. 303-304",2010,Sept.
"Takashi Nose,Yuhei Ota,Takao Kobayashi","HMM-based voice conversion using quantized F0 context",,"IEICE Trans. on Information and Systems","The Institute of Electronics, Information and Communication Engineers","Vol. E93-D","No. 9","pp. 2483-2490",2010,Sept.
"能勢 隆,小林隆夫","話者適応を用いたHMMに基づく不特定話者間声質変換","日本音響学会2010年秋季研究発表会","日本音響学会2010年秋季研究発表会講演論文集","日本音響学会",,,"pp. 283-284",2010,Sept.
"能勢 隆,小林隆夫","適応F0量子化によるHMM声質変換の品質改善","日本音響学会2010年秋季研究発表会","日本音響学会2010年秋季研究発表会講演論文集","日本音響学会",,,"pp. 285-288",2010,Sept.
"Takashi Nose,Takao Kobayashi","HMM-based robust voice conversion using adaptive F0 quantization","Seventh ISCA Tutorial and Research Workshop on Speech Synthesis, SSW7","Proc. 7th ISCA Workshop on Speech Synthesis","The International Speech Communication Association","Vol. SSW7-2010",,"pp. 80-85",2010,Sept.
"横溝秀始,能勢 隆,小林隆夫","HMMに基づく英語音声合成の韻律コンテキストの評価","日本音響学会2010年秋季研究発表会","日本音響学会2010年秋季研究発表会講演論文集","日本音響学会",,,"pp. 409-410",2010,Sept.
"Shuji Yokomizo,Takashi Nose,Takao Kobayashi","Evaluation of prosodic contextual factors for HMM-based speech synthesis","INTERSPEECH 2010","Proc. 11th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 430-433",2010,Sept.
"横溝秀始,能勢 隆,小林隆夫","HMM音声合成における韻律コンテキストの評価","日本音響学会2010年春季研究発表会","日本音響学会2010年春季研究発表会講演論文集","日本音響学会",,,"pp. 403-404",2010,Mar.
"太田悠平,能勢 隆,小林隆夫","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","日本音響学会2010年春季研究発表会","日本音響学会2010年春季研究発表会講演論文集","日本音響学会",,,"pp. 327-328",2010,Mar.
"大木康次郎,能勢 隆,小林隆夫","量子化F0韻律コンテキストを用いたHMM音声合成の評価","日本音響学会2010年春季研究発表会","日本音響学会2010年春季研究発表会講演論文集","日本音響学会",,,"pp. 341-342",2010,Mar.
"Takashi Nose,Koujirou Ooki,Takao Kobayashi","HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model","ICASSP 2010","Proc. 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing",,,,"pp. 4622-4625",2010,Mar.
"Takao Kobayashi","Speech Signal Processing Toolkit (SPTK)",,"Computer Processing of Asian Spoken Languages","Consideration Books",,,"pp. 301-304",2010,Mar.
"郡山知樹,能勢 隆,小林隆夫","HMMに基づく対話音声合成のための発話単位の検討","日本音響学会2010年春季研究発表会","日本音響学会2010年春季研究発表会講演論文集","日本音響学会",,,"pp. 143-144",2010,Mar.
"郡山知樹,能勢 隆,小林隆夫","平均声に基づく対話音声合成に関する検討",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 109","No. 375","pp. SP2009-100, 33-38",2010,Jan.
"Yusuke Ijima,Takashi Nose,Makoto Tachibana,Takao Kobayashi","A rapid model adaptation technique for emotional speech recognition with style estimation based on multiple-regression HMM",,"IEICE Trans. on Information and Systems","The Institute of Electronics, Information and Communication Engineers","Vol. E93-D","No. 1","pp. 107-115",2010,Jan.
"Takashi Nose,Takao Kobayashi","A technique for estimating intensity of emotional expressions and speaking styles in speech based on multiple-regression HSMM",,"IEICE Trans. on Information and Systems","The Institute of Electronics, Information and Communication Engineers","Vol. E93-D","No. 1","pp. 116-124",2010,Jan.
"太田悠平,能勢 隆,小林隆夫","F0量子化と非パラレル学習に基づく声質変換の評価",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 109","No. 375","pp. SP2009-100, 27-32",2010,Jan.
"Takao Kobayashi","Special section on processing natural speech variability for improved verbal human-computer interaction",,"IEICE Transactions on Information and Systems",,"Vol. E93-D","No. 9","pp. 2347",2010,
"大木康次郎,能勢 隆,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 109","No. 356","pp. SP2009-87, 141-146",2009,Dec.
"太田悠平,能勢 隆,小林隆夫","F0量子化と非パラレル学習に基づく声質変換の検討",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 109","No. 356","pp. SP2009-91, 171-176",2009,Dec.
"大木康次郎,能勢 隆,小林隆夫","HMM音声合成におけるF0モデルの教師なし学習の検討",,"日本音響学会2009年秋季研究発表会講演論文集",,,,"pp. 259-260",2009,Sept.
"郡山知樹,能勢 隆,小林隆夫","HMMに基づく対話音声合成の検討",,"日本音響学会2009年秋季研究発表会講演論文集",,,,"pp. 255-256",2009,Sept.
"Takashi Nose,Junichi Asada,Takao Kobayashi","HMM-based speaker characteristics emphasis using average voice model","INTERSPEECH 2009","Proc. 10th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 2631-2634",2009,Sept.
"Yusuke Ijima,Takeshi Matsubara,Takashi Nose,Takao Kobayashi","Speaking style adaptation for spontaneous speech recognition using multiple-regression HMM","INTERSPEECH 2009","Proc. 10th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 552-555",2009,Sept.
"太田悠平,能勢 隆,小林隆夫","F0量子化と非パラレル学習に基づく声質変換",,"日本音響学会2009年秋季研究発表会講演論文集",,,,"pp. 289-290",2009,Sept.
"能勢 隆,松原 健,井島勇祐,小林隆夫","重回帰HMMに基づく自然発話音声の発話様式識別",,"電子情報通信学会技術研究報告",,"Vol. 109","No. 139","pp. SP2009-46, 31-36",2009,July
"Suphattharachai Chomphan,Takao Kobayashi","Tone correctness improvement in speaker-independent average-voice-based Thai speech synthesis",,"Speech Communication","Elsevier","vol. 51","no. 4","pp. 330-343",2009,Apr.
"Yusuke Ijima,Makoto Tachibana,Takashi Nose,Takao Kobayashi","Emotional speech recognition based on style estimation and adaptationwith multiple-regression HMM","ICASSP 2009","Proc. 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing",,,,"pp. 4157-4160",2009,Apr.
"井島勇祐,橘 誠,能勢 隆,小林隆夫","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","日本音響学会2009年春季研究発表会","日本音響学会2009年春季研究発表会講演論文集","日本音響学会",,,"pp. 187-188",2009,Mar.
"松原 健,井島勇祐,橘 誠,能勢 隆,小林隆夫","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","日本音響学会2009年春季研究発表会","日本音響学会2009年春季研究発表会講演論文集","日本音響学会",,,"pp. 189-190",2009,Mar.
"橘 誠,河野明文,能勢 隆,小林隆夫","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","日本音響学会2009年春季研究発表会","日本音響学会2009年春季研究発表会講演論文集","日本音響学会",,,"pp. 293-296",2009,Mar.
"浅田惇一,能勢 隆,橘 誠,小林隆夫","平均声に基づく音声合成における話者強調の検討","日本音響学会2009年春季研究発表会","日本音響学会2009年春季研究発表会講演論文集","日本音響学会",,,"pp. 297-298",2009,Mar.
"太田悠平,能勢 隆,小林隆夫","F0量子化を用いたMSD-HMMに基づく声質変換","日本音響学会2009年春季研究発表会","日本音響学会2009年春季研究発表会講演論文集","日本音響学会",,,"pp. 307-308",2009,Mar.
"Takashi Nose,Makoto Tachibana,Takao Kobayashi","HMM-based style control for expressive speech synthesis with arbitrary speaker's voice using model adaptation",,"IEICE Trans. on Information and Systems","The Institute of Electronics, Information and Communication Engineers","Vol. E92-D","No. 3","pp. 489-497",2009,Mar.
"花井早紀,橘 誠,小林隆夫","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","電子情報通信学会2009年総合大会","電子情報通信学会2009年総合大会講演論文集","電子情報通信学会",,,"p. 176",2009,Mar.
"Junichi Yamagishi,Takao Kobayashi,Yuji Nakano,Katsumi Ogata,Juri Isogai","Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm",,"IEEE Trans. on Audio, Speech, and Language Processing","IEEE","Vol. 17","No. 1","pp. 66-83",2009,Jan.
"井島勇祐,橘 誠,能勢 隆,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 108","No. 338","pp. SP2008-85, 37-42",2008,Dec.
"Yusuke Ijima,Makoto Tachibana,Takashi Nose,Takao Kobayashi","An on-line adaptation technique for emotional speech recognition using style estimation with multiple-regression HMM","INTERSPEECH 2008","Proc. 9th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 1297-1300",2008,Sept.
"Takashi Nose,Yoichi Kato,Makoto Tachibana,Takao Kobayashi","An estimation technique of style expressiveness for emotional speech using model adaptation based on multiple-regression HSMM","INTERSPEECH 2008","Proc. 9th Annual Conference of the International Speech Communication Association","The International Speech Communication Association",,,"pp. 2759-2762",2008,Sept.
"河野明文,橘 誠,能勢 隆,小林隆夫","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","日本音響学会2008年秋季研究発表会","日本音響学会2008年秋季研究発表会講演論文集","日本音響学会",,,"pp. 253-254",2008,Sept.
"井島勇祐,橘 誠,能勢 隆,小林隆夫","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","日本音響学会2008年秋季研究発表会","日本音響学会2008年秋季研究発表会講演論文集","日本音響学会",,,"pp. 131-132",2008,Sept.
"井島勇祐,橘 誠,能勢 隆,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 108","No. 142","pp. SP2008-48, 31-36",2008,July
"市川清人,三田雄志,堀 修,小林隆夫","顔パーツを利用した隠れを含む顔の検出方法",,"画像電子学会誌","画像電子学会","Vol. 37","No. 4","pp. 419-427",2008,July
"橘 誠,河野明文,能勢 隆,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 108","No. 265","pp. SP2008-63, 41-46",2008,July
"Suphattharachai Chomphan,Takao Kobayashi","Tone correctness improvement in speaker dependent HMM-based Thai speech synthesis",,"Speech Communication","Elsevier","vol. 50","no. 5","pp. 392-404",2008,May
"Junichi Yamagishi,Hisashi Kawai,Takao Kobayashi","Phone duration modeling using gradient tree boosting",,"Speech Communication","Elsevier","vol. 50","no. 5","pp. 405-415",2008,May
"Suphattharachai Chomphan,Takao Kobayashi","Incorporation of phrase intonation to context clustering for average voice models in HMM-based Thai speech synthesis","ICASSP 2008","Proc. 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing","IEEE",,,"pp. 4637-4640",2008,Apr.
"Makoto Tachibana,Shinsuke Izawa,Takashi Nose,Takao Kobayashi","Speaker and style adaptation using average voice model for style control in HMM-based speech synthesis","ICASSP 2008","Proc. 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing","IEEE",,,"pp. 4633-4636",2008,Apr.
"山岸順一,能勢 隆,全 炳河,戸田 智基,徳田 恵一,小林隆夫","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","日本音響学会2008年春季研究発表会","日本音響学会2008年春季研究発表会講演論文集","日本音響学会",,,"pp. 339-342",2008,Mar.
"井澤信介,能勢 隆,橘 誠,小林隆夫","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","日本音響学会2008年春季研究発表会","日本音響学会2008年春季研究発表会講演論文集","日本音響学会",,,"pp. 359-360",2008,Mar.
"Kiyoto Ichikawa,Takeshi Mita,Osamu Hori,Takao Kobayashi","Component-based face detection method for various types of occluded faces","ISCCSP 2008","Proc. 2008 3rd International Symposium on Communications, Control, and Signal Processing","IEEE",,,"pp. 538-543",2008,Mar.
"Suphattharachai Chomphan,Takao Kobayashi","A context clustering technique for improvement of tone intelligibility of average-voice-based Thai speech synthesis","Asian Workshop on Speech Science and Technology","IEICE Technical Report","The Institute of Electronics, Information and Communication Engineers","Vol. 107","No. 551","pp. SP2007-194, 45-50",2008,Mar.
"後藤達哉,能勢 隆,小林隆夫","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","日本音響学会2008年春季研究発表会","日本音響学会2008年春季研究発表会講演論文集","日本音響学会",,,"pp. 399-400",2008,Mar.
"加藤陽一,能勢 隆,橘 誠,小林隆夫","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","日本音響学会2008年春季研究発表会","日本音響学会2008年春季研究発表会講演論文集","日本音響学会",,,"pp. 231-232",2008,Mar.
"大川高志,能勢 隆,小林隆夫","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","日本音響学会2008年春季研究発表会","日本音響学会2008年春季研究発表会講演論文集","日本音響学会",,,"pp. 343-344",2008,Mar.
"橘 誠,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 107","No. 356","pp. SP2007-87, 7-12",2007,Nov.
"井澤信介,橘 誠,能勢 隆,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 107","No. 282","pp. SP2007-85, 81-86",2007,Oct.
"Takashi Nose,Junichi Yamagishi,Takashi Masuko,Takao Kobayashi","A style control technique for HMM-based expressive speech synthesis",,"IEICE Trans. on Information and Systems","The Institute of Electronics, Information and Communication Engineers","Vol. E90-D","No. 9","pp. 1406-1413",2007,Sept.
"能勢 隆,小林隆夫","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","日本音響学会2007年秋季研究発表会","日本音響学会2007年秋季研究発表会講演論文集","日本音響学会",,,"pp. 363-364",2007,Sept.
"井澤信介,能勢 隆,橘 誠,小林隆夫","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","日本音響学会2007年秋季研究発表会","日本音響学会2007年秋季研究発表会講演論文集","日本音響学会",,,"pp. 315-316",2007,Sept.
"橘 誠,井澤信介,小林隆夫","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","日本音響学会2007年秋季研究発表会","日本音響学会2007年秋季研究発表会講演論文集","日本音響学会",,,"pp. 409-410",2007,Sept.
"Suphattharachai Chomphan,Takao Kobayashi","Design of tree-based context clustering for an HMM-based Thai speech synthesis system","Sixth ISCA Tutorial and Research Workshop on Speech Synthesis, SSW6","Proc. 6th ISCA Workshop on Speech Synthesis","The International Speech Communication Association","Vol. SSW6-2007",,"pp. 160-165",2007,Aug.
"Makoto Tachibana,Keigo Kawashima,Junichi Yamagishi,Takao Kobayashi","Performance evaluation of HMM-based style classification with a small amount of training data","INTERSPEECH 2007","Proc. 8th Annual Conference of the International Speech Communication Association","The International Speech Communication Association","Vol. INTERSPEECH 2007",,"pp. 2261-2264",2007,Aug.
"Takashi Nose,Yoichi Kato,Takao Kobayashi","Style estimation of speech based on multiple regression hidden semi-Markov model","INTERSPEECH 2007","Proc. 8th Annual Conference of the International Speech Communication Association","The International Speech Communication Association","Vol. INTERSPEECH 2007",,"pp. 2285-2288",2007,Aug.
"Suphattharachai Chomphan,Takao Kobayashi","Implementation and evaluation of an HMM-based Thai speech synthesis system","INTERSPEECH 2007","Proc. 8th Annual Conference of the International Speech Communication Association","The International Speech Communication Association","Vol. INTERSPEECH 2007",,"pp. 2849-2852",2007,Aug.
"Junichi Yamagishi,Takao Kobayashi,Steve Renals,Simon King,Heiga Zen,Tomoki Toda,Keiichi Tokuda","Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV","Sixth ISCA Tutorial and Research Workshop on Speech Synthesis, SSW6","Proc. 6th ISCA Workshop on Speech Synthesis","The International Speech Communication Association","Vol. SSW6-2007",,"pp. 125-130",2007,Aug.
"橘 誠,川島啓吾,小林隆夫","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",,"電子情報通信学会技術研究報告","電子情報通信学会","Vol. 107","No. 158","pp. NLC2007-4, 19-24",2007,July
"Heiga Zen,Keiichi Tokuda,Takashi Masuko,Takao Kobayashi,Tadashi Kitamura","A Hidden semi-Markov model-based speech synthesis system",,"IEICE Trans. on Information and Systems","The Institute of Electronics, Information and Communication Engineers","Vol. E90-D","No. 5","pp. 825-834",2007,May
"Junichi Yamagishi,Takao Kobayashi,Makoto Tachibana,Katsumi Ogata,Yuji Nakano","Model adaptation approach to speech synthesis with diverse voices and styles","ICASSP 2007","Proc. 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing","IEEE","Vol. ICASSP 2007",,"pp. 1233-1236",2007,Apr.
"Takashi Nose,Yoichi Kato,Takao Kobayashi","A speaker adaptation technique for MRHSMM-based style control of synthetic speech","ICASSP 2007","Proc. 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing","IEEE","Vol. ICASSP 2007",,"pp. 833-836",2007,Apr.
"井澤信介,能勢 隆,山岸順一,小林隆夫","合成音声のスタイル制御における話者適応の評価","日本音響学会2007年春季研究発表会","日本音響学会2007年春季研究発表会講演論文集","日本音響学会",,,"pp. 269-270",2007,Mar.
"大川高志,緒方克海,山岸順一,小林隆夫","平均声に基づく音声合成における合成音声の品質評価","日本音響学会2007年春季研究発表会","日本音響学会2007年春季研究発表会講演論文集","日本音響学会",,,"pp. 193-194",2007,Mar.
"橘 誠,井澤信介,能勢隆,小林隆夫","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","日本音響学会2007年春季研究発表会","日本音響学会2007年春季研究発表会講演論文集","日本音響学会",,,"pp. 195-196",2007,Mar.
"加藤陽一,河野明文,能勢隆,小林隆夫","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","日本音響学会2007年春季研究発表会","日本音響学会2007年春季研究発表会講演論文集","日本音響学会",,,"pp. 267-268",2007,Mar.
"川島啓吾,小林隆夫","不明確性を含む動作表現のためのモデル構築法の検討","電子情報通信学会2007年総合大会","電子情報通信学会2007年総合大会講演論文集","電子情報通信学会",,,"p. 188",2007,Mar.
"Heiga Zen,Takashi Masuko,Keiichi Tokuda,Takashi Yoshimura,Takao Kobayashi,Tadashi Kitamura","State duration modeling for HMM-based speech synthesis",,"IEICE Trans. on Information and Systems","The Institute of Electronics, Information and Communication Engineers","Vol. E90-D","No. 3","pp. 692-693",2007,Mar.
"Junichi Yamagishi,Takao Kobayashi","Average-voice-based speech synthesis using HSMM-based speaker adaptation and adaptive training",,"IEICE Trans. on Information and Systems","The Institute of Electronics, Information and Communication Engineers","Vol. E90-D","No. 2","pp. 533-543",2007,Feb.
"緒方克海,橘 誠,山岸順一,小林隆夫","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",,"電子情報通信学会技術研究報告",,"Vol. 106","No. 333","pp. SP2006-84, 49-54",2006,Nov.
"Katsumi Ogata,Makoto Tachibana,Junichi Yamagishi,Takao Kobayashi","Acoustic model training based on linear transformation and MAP modification for HSMM-based speech synthesis",,"Proc. 9th International Conference on Spoken Language Processing",,"Vol. INTERSPEECH 2006 - ICSLP",,"pp. 1328-1331",2006,Sept.
"Takashi Nose,Junichi Yamagishi,Takao Kobayashi","A style control technique for speech synthesis using multiple regression HSMM",,"Proc. 9th International Conference on Spoken Language Processing",,"Vol. INTERSPEECH 2006 - ICSLP",,"pp. 1324-1327",2006,Sept.
"大川高志,緒方克海,山岸順一,小林隆夫","線形変換とMAPに基づく音響モデル学習法の評価",,"日本音響学会2006年秋季研究発表会講演論文集",,,"No. 1-Q-14","pp. 265-266",2006,Sept.
"Yuji Nakano,Makoto Tachibana,Junichi Yamagishi,Takao Kobayashi","Constrained structural maximum a posteriori linear regression for average-voice-based speech synthesis",,"Proc. 9th International Conference on Spoken Language Processing",,"Vol. INTERSPEECH 2006 - ICSLP",,"pp. 2286-2289",2006,Sept.
"Makoto Tachibana,Takashi Nose,Junichi Yamagishi,Takao Kobayashi","A technique for controlling voice quality of synthetic speech using multiple regression HSMM",,"Proc. 9th International Conference on Spoken Language Processing",,"Vol. INTERSPEECH 2006 - ICSLP",,"pp. 2438-2441",2006,Sept.
"井澤信介,能勢 隆,山岸順一,小林隆夫","合成音声のスタイル制御における話者適応の検討",,"日本音響学会2006年秋季研究発表会講演論文集",,,"No. 1-Q-9","pp. 255-256",2006,Sept.
"橘 誠,能勢 隆,小林隆夫","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",,"日本音響学会2006年秋季研究発表会講演論文集",,,"No. 1-Q-10","pp. 257-258",2006,Sept.
"Junichi Yamagishi,Katsumi Ogata,Yuji Nakano,Juri Isogai,Takao Kobayashi","HSMM-based model adaptation algorithms for average-voice-based speech synthesis",,"Proc. 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing",,"Vol. ICASSP 2006",,"pp. 77-80",2006,May
"橘 誠,能勢 隆,山岸順一,小林隆夫","重回帰HSMMに基づく合成音声の声質制御の検討",,"日本音響学会2006年春季研究発表会講演論文集",,,"No. 2-4-18","pp. 297-298",2006,Mar.
"能勢 隆,山岸順一,小林隆夫","重回帰HSMMに基づく音声の発話様式・感情表現の推定",,"日本音響学会2006年春季研究発表会講演論文集",,,"No. 1-4-4","pp. 219-220",2006,Mar.
"緒方克海,中野雄資,山岸順一,小林隆夫","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",,"日本音響学会2006年春季研究発表会講演論文集",,,"No. 2-4-19","pp. 299-300",2006,Mar.
"川島啓吾,橘 誠,山岸順一,小林隆夫","MSD-HMMを用いた音声のスタイル識別手法の評価",,"日本音響学会2006年春季研究発表会講演論文集",,,"No. 1-P-11","pp. 165-166",2006,Mar.
"Makoto Tachibana,Junichi Yamagishi,Takashi Masuko,Takao Kobayashi","A style adaptation technique for speech synthesis using HSMM and suprasegmental features",,"IEICE Trans. on Information and Systems",,"Vol. E89-D","No. 3","pp. 1092-1099",2006,Mar.
"中野雄資,緒方克海,山岸順一,小林隆夫","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",,"日本音響学会2006年春季研究発表会講演論文集",,,"No. 1-Q-26","pp. 385-386",2006,Mar.
"山岸順一,小林隆夫","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",,"日本音響学会2006年春季研究発表会講演論文集",,,"No. 2-4-20","pp. 301-302",2006,Mar.
"小林隆夫（分担）,広瀬啓吉編著","韻律と音声言語情報処理",,,"丸善",,,"pp. 128-138",2006,Jan.
"能勢 隆,山岸順一,小林隆夫","重回帰HSMMを用いた合成音声のスタイル制御",,"電子情報通信学会技術研究報告",,"Vol. 105","No. 572","pp. SP2005-160, 61-66",2006,Jan.
"岡崎雅嗣,国本利文,小林隆夫","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",,"電子情報通信学会論文誌",,"Vol. J88-D-II","No. 12","pp. 2301-2310",2005,Dec.
"川島啓吾,橘 誠,山岸順一,小林隆夫","MSD-HMMに基づく音声のスタイル識別",,"電子情報通信学会技術研究報告",,"Vol. 105","No. 496","pp. SP2005-136, 151-156",2005,Dec.
"小林隆夫（分担）,人工知能学会編","人工知能学辞典",,,"共立出版",,,"pp. 459-462",2005,Dec.
"Naotake Niwase,Junichi Yamagishi,Takao Kobayashi","Human walking motion synthesis with desired pace and stride length based on HSMM",,"IEICE Trans. Information and Systems",,"Vol. E88-D","No. 11","pp. 2492-2499",2005,Nov.
"Takashi Yamazaki,Naotake Niwase,Junichi Yamagishi,Takao Kobayashi","Human walking motion synthesis based on multiple regression hidden semi-Markov model","Second International Workshop on Language Understanding and Agents for Real World Interaction, LUAR 2005","Proc. 2005 International Conference on Cyberworlds",,"Vol. CW2005",,"pp. 445-452",2005,Nov.
"Makoto Tachibana,Junichi Yamagishi,Takashi Masuko,Takao Kobayashi","Speech synthesis with various emotional expressions and speaking styles by style interpolation and morphing",,"IEICE Trans. Information and Systems",,"Vol. E88-D","No. 11","pp. 2484-2491",2005,Nov.
"小林隆夫","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","日本音響学会2005年秋季研究発表会","日本音響学会2005年秋季研究発表会講演論文集",,,"No. 2-6-12","pp. 283-286",2005,Sept.
"川島啓吾,山岸順一,小林隆夫","MSD-HMMを用いた音声のスタイル識別の検討","日本音響学会2005年秋季研究発表会","日本音響学会2005年秋季研究発表会講演論文集",,,"No. 1-P-24","pp. 199-200",2005,Sept.
"中野雄資,緒方克海,磯貝朱里,山岸順一,小林隆夫","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","日本音響学会2005年秋季研究発表会","日本音響学会2005年秋季研究発表会講演論文集",,,"No. 1-Q-11","pp. 395-396",2005,Sept.
"橘 誠,山岸順一,小林隆夫","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","日本音響学会2005年秋季研究発表会","日本音響学会2005年秋季研究発表会講演論文集",,,"No. 2-6-14","pp. 289-290",2005,Sept.
"磯貝朱里,山岸順一,小林隆夫","HMM音声合成におけるESATアルゴリズムの評価","日本音響学会2005年秋季研究発表会","日本音響学会2005年秋季研究発表会講演論文集",,,"No. 3-6-23","pp. 373-374",2005,Sept.
"山岸順一,河井 恒,小林隆夫","Naive Markov Modelによるポーズ予測アルゴリズム","日本音響学会2005年秋季研究発表会","日本音響学会2005年秋季研究発表会講演論文集",,,"No. 3-6-11","pp. 349-350",2005,Sept.
"能勢 隆,山岸順一,小林隆夫","重回帰HSMMを用いた音声のスタイル制御法の検討",,"日本音響学会2005年秋季研究発表会講演論文集",,,"No. 2-6-13","pp. 287-288",2005,Sept.
"Vladimir Braquet,Takao Kobayashi","A Wavelet based noise reduction algorithm for speech signal corrupted by coloured noise","The 9th European Conference on Speech Communication and Technology, INTERSPEECH 2005","Proc. 9th European Conference on Speech Communication and Technology",,"Vol. INTERSPEECH 2005",,"pp. 2073-2076",2005,Sept.
"Juri Isogai,Junichi Yamagishi,Takao Kobayashi","Model adaptation and adaptive training using ESAT algorithm for HMM-based speech synthesis","The 9th European Conference on Speech Communication and Technology, INTERSPEECH 2005","Proc. 9th European Conference on Speech Communication and Technology",,"Vol. INTERSPEECH 2005",,"pp. 2597-2600",2005,Sept.
"Makoto Tachibana,Junich Yamagishi,Takashi Masuko,Takao Kobayashi","Performance evaluation of style adaptation for hidden semi-Markov model based speech synthesis","The 9th European Conference on Speech Communication and Technology, INTERSPEECH 2005","Proc. 9th European Conference on Speech Communication and Technology",,"Vol. INTERSPEECH 2005",,"pp. 2805-2808",2005,Sept.
"中野雄資,緒方克海,磯貝朱里,山岸順一,小林隆夫","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","日本音響学会2005年秋季研究発表会","日本音響学会2005年秋季研究発表会講演論文集",,,"No. 1-Q-11","pp. 395-396",2005,Sept.
"山岸順一,河井 恒,平井俊男,小林隆夫","アンサンブル学習に基づく音韻継続長のモデル化","電子情報通信学会・日本音響学会 音声研究会","電子情報通信学会技術研究報告",,"Vol. 105","No. SP2005-53","pp. 7-12",2005,Aug.
"橘 誠,山岸順一,小林隆夫","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",,"電子情報通信学会技術研究報告",,"Vol. 105","No. SP2005-51","pp. 29-34",2005,Aug.
"磯貝朱里,緒方克海,中野雄資,山岸順一,小林隆夫","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",,"電子情報通信学会技術研究報告",,"Vol. 105","No. SP2005-50","pp. 23-28",2005,Aug.
"古宮弘智,庭瀬尚武,小林隆夫","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","電子情報通信学会2005年総合大会","電子情報通信学会2005年総合大会講演論文集",,,"No. D-12-60","pp. 210",2005,Mar.
"庭瀬尚武,山岸順一,小林隆夫","歩行速度とテンポを考慮した歩行動作の生成","電子情報通信学会2005年総合大会","電子情報通信学会2005年総合大会講演論文集",,,"No. D-12-118","pp. 268",2005,Mar.
"Dhany Arifianto,Takao Kobayashi","Voiced/Unvoiced determination of speech signal in noisy environment using harmonicity measure based on instantaneous frequency","2005 IEEE International Conference on Acoustics, Speech, and Signal Processing","Proc. 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing",,"Vol. ICASSP 2005",,"pp. 877-880",2005,Mar.
"Junichi Yamagishi,Koji Onishi,Takashi Masuko,Takao Kobayashi","Acoustic modeling of speaking styles and emotional expressions in HMM-based speech synthesis",,"IEICE Trans. Information and Systems",,"Vol. E88-D","No. 3","pp. 502-509",2005,Mar.
"山岸順一,小林隆夫","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","日本音響学会2005年春季研究発表会","日本音響学会2005年春季研究発表会講演論文集",,"Vol. I","No. 1-1-17","pp. 187-188",2005,Mar.
"磯貝朱里,山岸順一,小林隆夫","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","日本音響学会2005年春季研究発表会","日本音響学会2005年春季研究発表会講演論文集",,"Vol. I","No. 1-1-18","pp. 189-190",2005,Mar.