Flexible Speech Synthesis for Digital Media Production

• Project/Area Number: 17300063
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Perception information processing/Intelligent robotics
• Research Institution: Nagoya Institute of Technology
• Principal Investigator: TOKUDA Keiichi Nagoya Institute of Technology, 大学院・工学研究科, 教授 (20217483)
• Co-Investigator(Kenkyū-buntansha): KITAMURA Tadashi 名古屋工業大学, 大学院・工学研究科, 教授 (60114865) ; NANKAKU Yoshihiko 名古屋工業大学, 大学院・工学研究科, 助教 (80397497) ; TODA Tomoki 端科学技術大学院大学, 情報科学研究科, 助教 (90403328)
• Co-Investigator(Renkei-kenkyūsha): BLACK Alan カーネギーメロン大学, 言語技術研究所, 准教授
• Project Period (FY): 2005 – 2008
• Project Status: Completed (Fiscal Year 2008)
• Budget Amount: ¥16,970,000 (Direct Cost: ¥14,900,000、Indirect Cost: ¥2,070,000); Fiscal Year 2008: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000); Fiscal Year 2007: ¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000); Fiscal Year 2006: ¥3,900,000 (Direct Cost: ¥3,900,000); Fiscal Year 2005: ¥4,100,000 (Direct Cost: ¥4,100,000)
• Keywords: 音声合成 / メディアコンテンツ / 声質 / 発話様式 / HMM / 隠れマルコフモデル / 歌声合成 / 発話スタイル / 感情音声

Research Abstract

本研究は, 「ト書き」付きの台本を声優の如く, 自在な表現で読み上げることのできる音声合成装置の実現を目指し, 種々の声質、スタイルの音声を少量の音声データから作成する"柔軟な" 音声合成技術を開発した。音声のみに止まらず、歌声についても研究対象とした.

Research Products

• [Journal Article] Tech-Ware : HMM-Based Speech Synthesis Resources (2009)
  • Author(s): Heiga Zen, Keiichi Tokuda
  • Journal Title: IEEE Signal Processing Magazine
• [Journal Article] Re-cent development of the HMM-based speech synthesis system (HTS) (2009)
  • Author(s): Heiga Zen, Keiichiro Oura, Takashi Nose, Junichi Yamagishi, Shinji Sako, Tomoki Toda, Takashi Masuko, Alan W. Black, Keiichi Tokuda
  • Journal Title: 2009 APSIPA Annual Summit and Con-ference, Sapporo Convention Center, Sapporo, Japan (to be published)
  • NAID: 110006549591
  • Peer Reviewed
• [Journal Article] Variational Bayesian method for HMM-based speech synthesis (2009)
  • Author(s): Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Journal Title: 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009) Pages: 4029-4032
  • Peer Reviewed
• [Journal Article] Minimum generation error training by using original spectrum as reference for log spectral distortion measure (2009)
  • Author(s): Yi-Jian Wu, Keiichi Tokuda
  • Journal Title: 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009) Pages: 4013-4016
  • Peer Reviewed
• [Journal Article] Voice conversion based on simultaneous modeling of spectrum and FO (2009)
  • Author(s): Kaori Yutani, Yosuke Uto, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
  • Journal Title: 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009) Pages: 3897-3900
  • Peer Reviewed
• [Journal Article] Statistical mapping between articulatory movements and acoustic spectrum with a Gaussian mixture model (2008)
  • Author(s): Tomoki Toda, Alan W. Black, and Keiichi Tokuda
  • Journal Title: Speech Communica-tion vol.50, no.3 Pages: 215-227
  • Peer Reviewed
• [Journal Article] Simultaneous Acoustic, Prosodic, and Phrasing Model Training for TTS Conversion Systems (2008)
  • Author(s): Keiichiro Oura, Yoshihiko Nankaku, Tomoki Toda, Keiichi Tokuda, Rannierry Maia, Shinsuke Sakai, Satoshi Nakamura
  • Journal Title: International Symposium on Chinese Spoken Language Processing (ISCSLP2008) Pages: 1-4
  • Peer Reviewed
• [Journal Article] Unsuper- vised Adaptation for HMM-Based Speech Synthesis (2008)
  • Author(s): Simon King, Keiichi Tokuda, Heiga Zen, Junichi Yamagishi
  • Journal Title: Interspeech 2008 Pages: 1869-1872
  • Peer Reviewed
• [Journal Article] Acoustic modeling with contextual additive structure for HMM-based speech recognition (2008)
  • Author(s): Yoshihiko Nankaku, Kazuhiro Naka- mura, Heiga Zen, Keiichi Tokuda
  • Journal Title: 2008 IEEE In- ternational Conference on Acous- tics, Speech, and Signal Processing (ICASSP 2008) Pages: 4469-4472
  • Peer Reviewed
• [Journal Article] Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM (2008)
  • Author(s): Tomoki Toda, Keiichi Tokuda
  • Journal Title: 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008) Pages: 3925-3928
  • Peer Reviewed
• [Journal Article] ON the state definition for a trainable excitation model in HMM-based speech synthesis (2008)
  • Author(s): Ranniery Maia, Tomoki Toda, Kei- ichi Tokuda, Shinsuke Sakai, Satoshi Nakamura
  • Journal Title: 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008) Pages: 3965-3968
  • Peer Reviewed
• [Journal Article] The Nitech-NAIST HMM based speech synthesis system for the Blizzard Challenge 2006 (2008)
  • Author(s): Heiga Zen, Tomoki Toda, Keiichi Tokuda
  • Journal Title: IEICE Transactions on Information Systems Vol. E91-D, no. 6 Pages: 1764-1773
  • NAID: 10026804444
  • Peer Reviewed
• [Journal Article] Statistical mapping between articulatory movements and acqustic spectrum with a Gaussian mixture model (2008)
  • Author(s): Tomoki Toda, Alan W.Black, and Keiichi Tokuda
  • Journal Title: Speech Communication vol.50,no.3 Pages: 215-227
  • Peer Reviewed
• [Journal Article] Voice conversion based on maximum likelihood estimation of speech parameter trajectory (2007)
  • Author(s): Tomoki Toda, Alan W. Black, and Keiichi Tokuda
  • Journal Title: IEEE Transactions on Audio, Speech and Language Processing vol.15, no.8 Pages: 2222-2235
  • Peer Reviewed
• [Journal Article] Hidden Semi-Markov Model Based Speech Syn-thesis System (2007)
  • Author(s): Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, and Tadashi Kitamura
  • Journal Title: IEICE Transactions on Information Systems vol.E90-D,no.5 Pages: 825-834
  • NAID: 110007519526
  • Peer Reviewed
• [Journal Article] Speech Parameter Generation Algo-rithm Considering Global Variance for HMM-Based Speech Synthesis (2007)
  • Author(s): Tomoki Toda and Keiichi Tokuda
  • Journal Title: IEICE Transactions on Information Systems vol.E90-D, no.5 Pages: 816-824
  • NAID: 110003298754
  • Peer Reviewed
• [Journal Article] Details of Nitech HMM-based speech synthesis system for the Blizzard Challenge 2005 (2007)
  • Author(s): Heiga Zen, Tomoki Toda, Masaru Nakamura, and Keiichi Tokuda
  • Journal Title: IEICE Transactions on Information and Systems vol.E90-D,no.1 Pages: 325-333
  • NAID: 110004071071
  • Peer Reviewed
• [Journal Article] Reformulating the HMM as a trajectory model by impos-ing explicit relationships between static and dynamic feature vector se-quences (2007)
  • Author(s): Heiga Zen, Keiichi Tokuda, Tadashi Kitamura
  • Journal Title: Computer Speech and Lan-guage vol.21, no.1 Pages: 153-173
  • Peer Reviewed
• [Journal Article] Voice conversion based on maximum likelihood estimation ofspeech parameter trajectory (2007)
  • Author(s): Tomoki Toda, Alan W.Black, and Keiichi Tokuda
  • Journal Title: IEEE Transactions on Audio, Speech andLanguage Processing vol.15,no.8 Pages: 2222-2235
  • Peer Reviewed
• [Journal Article] Hidden SemiMarkov Model Based Speech Synthesis System (2007)
  • Author(s): Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, and Tadashi Kitamura
  • Journal Title: IEICE Transactions on Informstion Systems vol.E90-D,no.5 Pages: 825-834
  • NAID: 110007519526
  • Peer Reviewed
• [Journal Article] Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis (2007)
  • Author(s): Tomoki Toda and Keiichi Tokuda
  • Journal Title: IEICE Transactionson Information Systems vol.E90-D,no.5 Pages: 816-824
  • NAID: 110003298754
  • Peer Reviewed
• [Journal Article] Details of Nitech HMM-based speech synthesis system for the Blizzard Challenge 2005 (2007)
  • Author(s): Heiga Zen, Tomoki Toda, Masaru Nakamura, Keiichi Tokuda
  • Journal Title: IEICE Transactions on Information and Systems vol.E90-D,no.1 Pages: 325-333
  • NAID: 110004071071
• [Journal Article] Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences (2007)
  • Author(s): Heiga Zen, Keiichi Tokuda, Tadashi Kitamura
  • Journal Title: Computer Speech and Language vol.20,no.1 Pages: 153-173
• [Journal Article] State Duration Modeling for HMM-Based Speech Synthesis (2007)
  • Author(s): Heiga Zen, Takashi Masuko, Keiichi Tokuda, Takayoshi Yoshimura, Takako Kobayashi, Tadashi Kitamura
  • Journal Title: IEICE Transactions on Information and Systems vol.E90-D,no.1 Pages: 692-693
  • NAID: 10004298360
• [Journal Article] HMM音声合成ツールキット ver. 2.0 (2007)
  • Author(s): 全炳河, 能勢隆, 山岸順一, 酒向慎司, 徳田恵一
  • Journal Title: 日本音響学会2007年春季研究発表会講演論文集 vol. I 、1-8-3 Pages: 197-198
• [Journal Article] Mixed excitation for HMM-based speech synthesis based on state-dependent filtering (2007)
  • Author(s): Ranniery Maia, Tomoki Toda, Heiga Zen, Yoshihiko Nankaku, Keiichi TOkuda
  • Journal Title: 日本音響学会2007年春季研究発表会講演論文集 vol. I 、1-8-4 Pages: 199-200
• [Journal Article] HMM音声克速のためのフィルタの高速化 (2007)
  • Author(s): 渡邊俊明, 全炳河, 南角吉彦, 李晃伸, 徳田恵一
  • Journal Title: 日本音響学会2007年春季研究発表会講演論文集 vol. I 、1-8-9 Pages: 209-210
• [Journal Article] HMM音声認識におけるコンテキストの加算的構造を考慮した音響モデリング (2007)
  • Author(s): 中村和寛, 全炳河, 南角吉彦, 李晃伸, 徳田恵一
  • Journal Title: 日本音響学会2007年春季研究発表会講演論文集 vol. I 、1-P-13 Pages: 149-150
• [Journal Article] 時系列マッチングを含む統計モデルに基づく声質変換 (2007)
  • Author(s): 中村憲一, 南角吉彦, 戸田智基, 徳田恵一
  • Journal Title: 日本音響学会2007年春季研究発表会講演論文集 vo1. I 、1-8-11 Pages: 213-214
• [Journal Article] An HMM-based Brazilian Portuguese speech synthesizer and its characteristics (2006)
  • Author(s): Ranniery Maia, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, and Fer-nando G. V. Resende
  • Journal Title: Journal of Communication and Infor-mation Systems vol.21, no.2 Pages: 58-71
  • Peer Reviewed
• [Journal Article] 音声合成研究も協調と競争の時代にITheBliz-zard Challenges (2006)
  • Author(s): 徳田恵一, アランブラック
  • Journal Title: 日本音響学会誌 vol.62, no.6 Pages: 466-472
  • Peer Reviewed
• [Journal Article] Speaker adaptation of trajectory HMMs using feature-space MLLR (2006)
  • Author(s): Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura
  • Journal Title: Interspeech 2006-ICLSP Pages: 1141-1144
  • Peer Reviewed
• [Journal Article] HMM-based singing voice synthesis system (2006)
  • Author(s): Keijiro Saino, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
  • Journal Title: Interspeech 2006-ICSLP Pages: 2274-2277
  • Peer Reviewed
• [Journal Article] An HMM-based Brazilian Portuguese speech synthesizer andits characteristics (2006)
  • Author(s): Ranniery Maia, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, and Fernando G.V.Resende
  • Journal Title: Journal of Communication and Information Systems vol.21,no.2 Pages: 132-145
  • Peer Reviewed
• [Journal Article] 大規模コーパスを用いた音声合成システムXIMERA (2006)
  • Author(s): 河井恒, 戸田智基, 山岸順一, 平井俊男, 倪晋富, 西澤信行, 津崎実, 徳田恵一
  • Journal Title: 電子情報通信学会論文誌(D-II) J89-D- II,no. 12 Pages: 2688-2698
  • NAID: 110007380404
• [Journal Article] 音声合成研究も協調と競争の時代に---The Blizzard Cnallenge--- (2006)
  • Author(s): 徳田恵一, アランブラック
  • Journal Title: 日本音響学会誌 vol.62,no.6 Pages: 466-472
• [Journal Article] Hyperparameter estimation for speech recognition based on variational Bayesian approach (2006)
  • Author(s): Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Journal Title: J. Acoust. Soc. Am. vol.120,no.5,Part.2 Pages: 3042-3042
• [Journal Article] Acoustic modeling with contextual additive structure for hidden Markov model-based speech recognition (2006)
  • Author(s): Kazuhiro Nakamura, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Journal Title: J. Acoust. Soc. Am. Vol.120,no.5,Part.2 Pages: 3042-3042
• [Journal Article] Speaker adaptation of trajectory HMMs using feature-space MLLR (2006)
  • Author(s): HEiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura
  • Journal Title: Interspeech 2006-ICLSP Pages: 1141-1144
• [Journal Article] HMM-based singing voice synthesis system (2006)
  • Author(s): Keijiro Saino, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
  • Journal Title: Interspeech 2006-ICLSP Pages: 2274-2277
• [Journal Article] Voice conversion based on mixtures of factor analyzers (2006)
  • Author(s): Yosuke Uto, Yoshihiko Nankaku, Tomoki Toda, Akinobu Lee, Keiichi Tokuda
  • Journal Title: Interspeech 2006-ICLSP Pages: 2278-2281
• [Journal Article] The Nitech-NAIST HMM-based speech synthesis system for the Blizzard Challenge 2006 (2006)
  • Author(s): Heiga Zen, Tomoki Toda, Keiichi Tokuda
  • Journal Title: Blizzard Challenge 2006 Warkshop
  • NAID: 10026804444
• [Journal Article] Developing a Test Bed of English Text-to-Speech System XIMERA for the Blizzard Challenge 2006 (2006)
  • Author(s): Tomoki Toda, Hisashi Kawai, Toshio Hirai, Jinfu Ni, Nobuyuki Nishizawa, Junichi Yamagishi, Minoru Tsuzaki, Keiichi Tokuda, Satoshi NAkamura
  • Journal Title: Blizzard Challenge 2006 Warkshop
• [Journal Article] Estimating trajectory HMM parameters using Monte Carlo EM with Gibbs sampler (2006)
  • Author(s): Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura
  • Journal Title: 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2006) vol.1
• [Journal Article] Hidden semi-Markov model based speech recognition system using weighted finite-state transducer (2006)
  • Author(s): Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
  • Journal Title: 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2006) vol.1
• [Journal Article] On the use of phonetic information for mapping from articulatory movements to vocal tract spectrum (2006)
  • Author(s): Kenichi Nakamura, Tomoki Toda, Yoshihiko Nankaku, Keiichi Tokuda
  • Journal Title: 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2006) vol.1
• [Journal Article] ICSLPにおける研究動向-音響モデル・音声合成を中心に- (2006)
  • Author(s): 全炳河, 南角吉彦, 戸田智基
  • Journal Title: 情報処理学会研究報告 2006-SLP-64 Pages: 179-184
  • NAID: 110006164218
• [Journal Article] HMM音声合成における特徴パラメータに関する検討 (2006)
  • Author(s): 丸目雅浩, 全炳河, 南角吉彦, 徳田恵一, 北村正
  • Journal Title: 日本音響学会2006年秋季研究発表会講演論文集 vol. I 、2-6-1 Pages: 185-186
• [Journal Article] The Nitech-NAIST HMM-based speech synthesis system for the Blizzard Challenge 2006 (2006)
  • Author(s): Heiga Zen, Tomoki Toda, Keiichi Tokuda
  • Journal Title: 日本音響学会2006年秋季研究発表会講演論文集 vol. I 、2-6-2 Pages: 187-188
  • NAID: 10026804444
• [Journal Article] Hidden Markov model-based speech synthesis as a tool for constructing communicative spoken dialog systems (2006)
  • Author(s): Keiichi Tokuda
  • Journal Title: J. Acoust. Soc. Am. Vol.120,no.5,Part.2 Pages: 3006-3006
• [Journal Article] ロボットの声 (2006)
  • Author(s): 徳田恵一
  • Journal Title: 電子情報通信学会本部・同当会支部平成17年度専門講習会『ロボットとIT技術-ロボットとのコミュニケーション』 (発表予定)
• [Journal Article] Estimating trajectory HMM parameters using Monte Carlo EM with Gibbs sampler (2006)
  • Author(s): Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura
  • Journal Title: 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2006) (accepted)
• [Journal Article] On the use of phonetic information for mapping from articulatory movements to vocal tract spectrum (2006)
  • Author(s): Kenichi Nakamura, Tomoki Toda, Yoshihiko Nankaku, Keiichi Tokuda
  • Journal Title: 2006 IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2006) (accepted)
• [Journal Article] Details of Nitech HMM-based speech synthesis system for Blizzard Challenge 2005(Blizzard Challenge 2005に向けたHMM音声合成システム) (2006)
  • Author(s): Heiga Zen, Tonioki Toda, Masaru Nakamura, Keiichi Tokuda(全炳河, 戸田智基, 中村勝, 徳田恵一)
  • Journal Title: 電子情報通信学会技術研究報告 (発表予定)
• [Journal Article] MFAに基づく声質変換 (2006)
  • Author(s): 宇藤陽介, 南角吉彦, 戸田智基, 李晃伸, 徳田恵一
  • Journal Title: 日本音響学会2006年春季研究発表会講演論文集 vol.I Pages: 239-240
• [Journal Article] コーパス・ベース多言語音声合成システムXIMERA (2006)
  • Author(s): 平井俊男, 戸田智基, 河井恒, 倪晋富, 西澤信行, 徳田恵一, 津崎実, 山岸順一
  • Journal Title: 日本音響学会2006年春季研究発表会講演論文集 vol.I Pages: 333-334
• [Journal Article] HMM-based European Portuguese TTS system (2005)
  • Author(s): Maria Joa o Barros, Ranniery Maia, Keiichi Tokuda, Fernando Gil Re- sende, Diamantino Freitas
  • Journal Title: INTERSPEECH 2005-EUROSPEECH Pages: 2581-2584
  • Peer Reviewed
• [Journal Article] 音声合成技術の最先端 (2005)
  • Author(s): 徳田恵一
  • Journal Title: 平成17年度電気関係学会東海支部連合大会 (CD-ROM proceeding)
• [Journal Article] The Blizzard Challenge- 2005: Evaluating corpus-based speech synthesis on common datasets (2005)
  • Author(s): Alan W.Black, Keiichi Tokuda
  • Journal Title: INTERSPEECH 2005 - EUROSPEECH Pages: 77-80
• [Journal Article] HMM-based European Portuguese TTS system (2005)
  • Author(s): Maria Joao Barros, Ranniery Maia, Keiichi Tokuda, Fernando Gil Resende, Diamantino Freitas
  • Journal Title: INTERSPEECH 2005 - EUROSPEECH Pages: 2581-2584
• [Journal Article] Speech parameter generation algorithm considering global variance for HMM-based speech synthesis (2005)
  • Author(s): Tomoki Toda, Keiichi Tokuda
  • Journal Title: INTERSPEECH 2005 - EUROSPEECH Pages: 2801-2804
  • NAID: 110003298754
• [Journal Article] HMM音声合成のための系列内変動を考慮した音声パラメータ生成アルゴリズム (2005)
  • Author(s): 戸田智基, 徳田恵一
  • Journal Title: 電子情報通信学会技術研究報告 vol.105・no.253 Pages: 1-6
  • NAID: 110003298754
• [Journal Article] コーパス・ベース音声合成システムXIMERA (2005)
  • Author(s): 平井俊男, 河井恒, 戸田智基, 山岸順一, 倪晋富, 西澤信行, 津崎実, 徳田恵一
  • Journal Title: 電子情報通信学会技術研究報告 vol.105・no.98 Pages: 37-42
  • NAID: 10016435789
• [Journal Article] 音声合成システムXIMERAによる対話音声の生成 (2005)
  • Author(s): 平井俊男, 山岸順一, 河井恒, 倪晋富, 西澤信行, 徳田恵一, 津崎実, 戸田智基
  • Journal Title: 日本音響学会2005年秋季研究発表会講演論文集 vol.I Pages: 269-270
• [Journal Article] トラジェクトリHMMのためのギブスサンプリングによるEM型学習アルゴリズム (2005)
  • Author(s): 全炳河, 南角吉彦, 徳田恵一
  • Journal Title: 日本音響学会2005年秋季研究発表会講演論文集 vol.I Pages: 89-90
• [Journal Article] 声道形状からスペクトルへの変換における音素情報利用に関する検討 (2005)
  • Author(s): 中村憲一, 戸田智基, 南角吉彦, 徳田恵一
  • Journal Title: 日本音響学会2005年秋季研究発表会講演論文集 vol.I Pages: 353-354
• [Journal Article] HMM音声合成における動的特徴量抽出法に関する検討 (2005)
  • Author(s): 中邨一仁, 南角吉彦, 徳田恵一, 北村正
  • Journal Title: 日本音響学会2005年秋季研究発表会講演論文集 vol.I Pages: 359-360
• [Journal Article] Blizzard Challenge 2005に向けたHMM音声合成システムの性能改善に関する評価 (2005)
  • Author(s): 中村勝, 全炳河, 戸田智基, 徳田恵一
  • Journal Title: 日本音響学会2005年秋季研究発表会講演論文集 vol.I Pages: 363-364
• [Journal Article] モーラ単位H/L型アクセントラベルに基づくHMM音声合成 (2005)
  • Author(s): 粉川久, 南角吉彦, 徳田恵一, 北村正
  • Journal Title: 日本音響学会2005年秋季研究発表会講演論文集 vol.I Pages: 365-366
• [Journal Article] トラジェクトリHMMの制約付き最尤線形回帰による話者適応 (2005)
  • Author(s): 全炳河, 南角吉彦, 徳田恵一, 北村正
  • Journal Title: 日本音響学会2005年秋季研究発表会講演論文集 vol.I Pages: 113-114
• [Journal Article] A robust speaker-adaptive HMM-based text-to-speec hsynthesis
  • Author(s): Junichi Yamagishi, Takashi Nose, Heiga Zen, Zhen-Hua Ling, Tomoki Toda, Keiichi Tokuda, Simon King, Steve Renals
  • Journal Title: IEEE Transactions on Au-dio, Speech and Language Processing (accepted)
  • Peer Reviewed
• [Journal Article] Statistical parametric speech synthesis
  • Author(s): Heiga Zen, Keiichi Tokuda, Alan W. Black
  • Journal Title: Speech Communication (accepted)
  • Peer Reviewed
• [Journal Article] Spectral conversion based on statistical models including time-frequency matching
  • Author(s): Yoshihiko Nankaku, Kenichi Naka mura, and Keiichi Tokuda
  • Journal Title: Proc. of 6th ISCA Speech Synthesis Workshop CD-ROM proceedings)
  • Peer Reviewed
• [Journal Article] Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences
  • Author(s): Heiga Zen, Kiichi Tokuda, Tadashi Kitamura
  • Journal Title: Computer Speech and Language (accepted)
• [Presentation] HMMに基づく歌声合成のためのビブラートモデル化 (2009)
  • Author(s): 山田知彦, 武藤聡, 南角吉彦, 酒向慎司, 徳田恵一
  • Organizer: 情報処理学会研究報告「音楽情報科学(MUS)」
  • Place of Presentation: (vol2009-MUS-80,no.5,IPSJ-MUSO9080005)
  • Year and Date: 2009-05-14
• [Presentation] ベイズ基準による隠れセミマルコフモデルに基づく音声合成 (2009)
  • Author(s): 橋本佳, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会
  • Place of Presentation: 東京工業大学
  • Year and Date: 2009-03-17
• [Presentation] HMM音声合成における発話内変動のモデル化手法に関する検討 (2009)
  • Author(s): 永尾京平, 全炳河, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会
  • Place of Presentation: 東京工業大学
  • Year and Date: 2009-03-17
• [Presentation] A decision tree-based clustering approach to state definition in a residual modeling framework (2009)
  • Author(s): Ranniery Maia, Tomoki Toda, Keiichi Tokuda, Shinsuke Sakai, Tohru Shimizu, Satoshi Nakamura
  • Organizer: 日本音響学会
  • Place of Presentation: 東京工業大学
  • Year and Date: 2009-03-17
• [Presentation] Variational Bayesian method for HMM-based speech synthesis (2009)
  • Author(s): Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2009)
  • Place of Presentation: 台湾 台北
• [Presentation] Minimum generation error training by using original spectrum as reference for log spectral distortion measure (2009)
  • Author(s): Yi-Jian Wu, Keiichi Tokuda
  • Organizer: 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2009)
  • Place of Presentation: 台湾 台北
• [Presentation] Voice conversion based on simultaneous modeling of spectrum and FO (2009)
  • Author(s): Kaori Yutani, Yosuke Uto, Yo shihiko Nankaku, Akinobu Lee, Keiichi Tokuda
  • Organizer: 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2009)
  • Place of Presentation: 台湾 台北
• [Presentation] FULL covariance state duration modeling for HMM-based speech synthesis (2009)
  • Author(s): Lu Heng, Wu Yi-Jian, Tokuda Keiichi, Dai Li-Rong, WangRen-Hua
  • Organizer: 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2009)
  • Place of Presentation: 台湾 台北
• [Presentation] Simultaneous Acoustic, Prosodic, and Phrasing Model Training for TTS Conversion Systems (2008)
  • Author(s): Keiichiro Oura, Yoshihiko Nankaku, Tomoki Toda, Keiichi Tokuda, Rannierry Maia, Shinsuke Sakai, Satoshi Nakamura
  • Organizer: International Symposium on Chinese Spoken Language Processing (ISCSLP2008)
  • Place of Presentation: 中国 昆明
  • Year and Date: 2008-12-17
• [Presentation] Cross-Lingual Speaker Adaptation for HMM-based Speech Synthesis (2008)
  • Author(s): Yi-Jian Wu, Simon King, Keiichi Tokuda
  • Organizer: International Symposium on Chinese Spoken Language Processing (ISCSLP2008)
  • Place of Presentation: 中国 昆明
  • Year and Date: 2008-12-17
• [Presentation] Bayesian Context Clustering Using Cross Validation for HMM-Based Speech Synthesis (2008)
  • Author(s): Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: 音声言語情報処理研究会
  • Place of Presentation: 早稲田大学
  • Year and Date: 2008-12-10
• [Presentation] Simultaneous Transformation of Duration and Spectrum Using Statistical Models Including Time-Sequence Matching (2008)
  • Author(s): Kaori Yutani, Yoshihiko Nankaku, Tomoki Toda, Keiichi Tokuda
  • Organizer: 音声言語情報処理研究会
  • Place of Presentation: 早稲田大学
  • Year and Date: 2008-12-10
• [Presentation] HMM音声合成における共分散パラメータの共有に関する検討 (2008)
  • Author(s): 大浦圭一郎, 全炳河, 南角吉彦, 李晃伸, 徳田恵一
  • Organizer: 音声言語情報処理研究会
  • Place of Presentation: 早稲田大学
  • Year and Date: 2008-12-10
• [Presentation] Analysis of stream-dependent tying structure for HMM-based speech synthesis (2008)
  • Author(s): Zhi-Peng Yu, Yi-Jian Wu, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: International Conference on Signal Processing (ICSP'08)
  • Place of Presentation: 中国 北京
  • Year and Date: 2008-10-28
• [Presentation] Unsupervised Adaptation for HMM-Based Speech Synthesis (2008)
  • Author(s): Simon King, Keiichi Tokuda, Heiga Zen, Junichi Yamagishi
  • Organizer: Interspeech 2008
  • Place of Presentation: オーストラリア ブリスベン
  • Year and Date: 2008-09-25
• [Presentation] Minimum Generation Error Training with Direct Log Spectral Distortion on LSPs for HMM-Based Speech Synthesis (2008)
  • Author(s): Yi-Jian Wu, Keiichi Tokuda
  • Organizer: Interspeech 2008
  • Place of Presentation: オーストラリア ブリスベン
  • Year and Date: 2008-09-24
• [Presentation] Bayesian Context Clustering Using Cross Valid Prior Distribution for HMM-Based Speech Recognition (2008)
  • Author(s): Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
  • Organizer: Interspeech 2008
  • Place of Presentation: オーストラリア ブリスペン
  • Year and Date: 2008-09-24
• [Presentation] Probabilistic Feature Mapping Based on Trajectory HMMs (2008)
  • Author(s): Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: Interspeech 2008
  • Place of Presentation: オーストラリア ブリスベン
  • Year and Date: 2008-09-24
• [Presentation] Simultaneous Conversion of Duration and Spectrum Based on Statistical Models Including Time-Sequence Matching (2008)
  • Author(s): Kaori Yutani, Yosuke Uto, Yoshihiko Nankaku, Tomoki Toda, Keiichi Tokuda
  • Organizer: Interspeech 2008
  • Place of Presentation: オーストラリア ブリスペン
  • Year and Date: 2008-09-24
• [Presentation] HTS-2008 : Yet another evaluation of speaker adaptive HMM-based speech synthesis system (2008)
  • Author(s): Junichi Yamagishi, Heiga Zen, Yi-Jian Wu, Tomoki Toda, Keiichi Tokuda
  • Organizer: Blizzard Challenge Workshop 2008
  • Place of Presentation: オーストラリア ブリスベン
  • Year and Date: 2008-09-21
• [Presentation] The NICT/ATR speech synthesis system for the Blizzard Challenge 2008 (2008)
  • Author(s): Ranniery Maia, Jinfu Ni, Shinsuke Sakai, Tomoki Toda, Keiichi TokudaTohru Shimizu, Satoshi Nakamura
  • Organizer: Blizzard Challenge Workshop 2008
  • Place of Presentation: オーストラリア ブリスペン
  • Year and Date: 2008-09-21
• [Presentation] 因子分析トラジェクトリHMMに基づく統計的音声スペクトル推定法 (2008)
  • Author(s): 戸田智基, 徳田恵一
  • Organizer: 日本音響学会
  • Place of Presentation: 九州大学
  • Year and Date: 2008-09-12
• [Presentation] 声質変換における時系列マッチングを含む統計モデルの拡張 (2008)
  • Author(s): 油谷かおり, 南角吉彦, 戸田智基, 徳田恵一
  • Organizer: 日本音響学会
  • Place of Presentation: 九州大学
  • Year and Date: 2008-09-11
• [Presentation] HMM音声合成における分散パラメータの共有に関する検討 (2008)
  • Author(s): 大浦圭一郎, 全炳河, 南角吉彦, 李晃伸, 徳田恵一
  • Organizer: 日本音響学会
  • Place of Presentation: 九州大学
  • Year and Date: 2008-09-11
• [Presentation] HMM training by minimizing log spectral distortion between generated and original LSPs for speech synthesis (2008)
  • Author(s): Yi-Jian Wu, Keiichi Tokuda
  • Organizer: 日本音響学会
  • Place of Presentation: 九州大学
  • Year and Date: 2008-09-10
• [Presentation] クロスバリデーションを用いたベイズ基準によるHMM音声合成 (2008)
  • Author(s): 橋本佳, 全炳河, 南角吉彦, 徳田恵一
  • Organizer: 日本音響学会
  • Place of Presentation: 九州大学
  • Year and Date: 2008-09-10
• [Presentation] The NICT/ATR-SLC entry for the Blizzard Challenge 2008 (2008)
  • Author(s): Ranniery Maia, Jinfu Ni, Shinsuke Sakai, Tomoki Toda, Keiichi Tokuda, Tohru Shimizu, Satoshi Nakamura
  • Organizer: 日本音響学会
  • Place of Presentation: 九州大学
  • Year and Date: 2008-09-10
• [Presentation] Acoustic modeling with contextual additive structure for HMM-based speech recognition (2008)
  • Author(s): Yoshihiko Nankaku, Kazuhiro Nakamura, Heiga Zen, Keiichi Tokuda
  • Organizer: 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP2008)
  • Place of Presentation: アメリカ ラスベガス
  • Year and Date: 2008-04-02
• [Presentation] 声質変換のためのスペクトルおよびF0の同時モデリング (2008)
  • Author(s): 宇藤 陽介, 南角 吉彦, 李 晃伸, 徳田 恵一
  • Organizer: 日本音響学会2008年春季研究発表会
  • Place of Presentation: 千葉工業大学
  • Year and Date: 2008-03-18
• [Presentation] 時系列マッチングを含む統計モデルに基づいた継続長およびスペクトルの同時変換 (2008)
  • Author(s): 油谷 かおり, 宇藤 陽介, 南角 吉彦, 戸田 智基, 李 晃伸, 徳田 恵一
  • Organizer: 日本音響学会2008年春季研究発表会
  • Place of Presentation: 千葉工業大学
  • Year and Date: 2008-03-18
• [Presentation] Blizzar 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 (2008)
  • Author(s): 能勢 隆, 山岸 順一, 全 柄河, 戸田 智基, 徳田 恵一
  • Organizer: 日本音響学会2008年春季研究発表会
  • Place of Presentation: 千葉工業大学
  • Year and Date: 2008-03-18
• [Presentation] 英語音声合成における韻律推定モデルと音響モデルの同時学習 (2008)
  • Author(s): 大浦 圭一郎, 戸田 智基, 南角 吉彦, 徳田 恵一, マイアハニエリ, 坂井 信輔, 中村 哲
  • Organizer: 日本音響学会2008年春季研究発表会
  • Place of Presentation: 千葉工業大学
  • Year and Date: 2008-03-18
• [Presentation] State clustering on an excitiation model for HMM-based speech synthesis (2008)
  • Author(s): Ranniery Maia, Tomoki Toda, Keiichi Tokuda, ShinsukeSakai, Satoshi Nakamura
  • Organizer: 日本音響学会2008年春季研究発表会
  • Place of Presentation: 千葉工業大学
  • Year and Date: 2008-03-18
• [Presentation] 声質と歌唱スタイルを自動学習可能な歌声合成システム (2008)
  • Author(s): 酒向 慎司, 才野 慶二郎, 南角 吉彦, 徳田 恵一, 北村 正
  • Organizer: 情報処理学会
  • Place of Presentation: 伊東温泉 ホテル暖香園
  • Year and Date: 2008-02-08
• [Presentation] 声質変換における時系列マッチングを含む統計モデルの拡張 (2008)
  • Author(s): 油谷かおり, 南角吉彦, 戸田智基, 徳田恵一
  • Organizer: 日本音響学会2008年秋季研究発表会
  • Place of Presentation: 日本音響学会ボスター賞(vol.I,2-p-24, 411-412)
• [Presentation] Performance evaluation of the speaker-independent HMM-based speech synthesis system HTS-2007 for the Blizzard Challenge 2007 (2008)
  • Author(s): Junichi Yamagishi, TakashiNose, Heiga Zen, TomokiToda, Keiichi Tokuda
  • Organizer: 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2008)
  • Place of Presentation: Las Vegas,Nevada,U.S.A
• [Presentation] Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM (2008)
  • Author(s): Tomoki Toda, Keiichi Tokuda
  • Organizer: 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2008)
  • Place of Presentation: Las Vegas,Nevada,U.S.A
• [Presentation] ON the state definition for a trainable excitation model in HMM-based speech synthesis (2008)
  • Author(s): Ranniery Maia, Tomoki Toda, Keiichi Tokuda, ShinsukeSakai, Satoshi Nakamura
  • Organizer: 2008 IEEE International Conference on Acoustics, Speech, and SignalProcessing(ICASSP 2008)
  • Place of Presentation: Las Vegas,Nevada,U.S.A
• [Presentation] Minimum generation error criterion considering globalllocal v.ariance for HMM-based speech synthesis (2008)
  • Author(s): Yi-Jian Wu, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2008)
  • Place of Presentation: Las Vegas,Nevada,U.S.A
• [Presentation] Recent development of the HMM-based speech synthesis system(HTS) (2007)
  • Author(s): Heiga Zen, Keiichiro Oura, Takashi Nose, Junichi Yamagishi, Shinji Sako, TomokiToda, Takashi Masuko, Alan W.Black, Keiichi Tokuda
  • Organizer: 電子情報通信学会(音声言語シンポジウム)
  • Place of Presentation: NTTけいはんな
  • Year and Date: 2007-12-21
• [Presentation] 変分ベイズ法に基づく声質変換 (2007)
  • Author(s): 丸目 雅浩, 南角 吉彦, 酒向 慎司, 徳田 恵一, 北村 正
  • Organizer: 電子情報通信学会(音声言語シンポジウム)
  • Place of Presentation: NTTけいはんな
  • Year and Date: 2007-12-21
• [Presentation] 声質変換のためのスペクトル・F0の同時モデリング (2007)
  • Author(s): 宇藤 陽介, 南角 吉彦, 李 晃伸, 徳田 恵一
  • Organizer: 電子情報通信学会(音声言語シンポジウム)
  • Place of Presentation: NTTけいはんな
  • Year and Date: 2007-12-20
• [Presentation] 因子分析に基づく固有声モデルを用いたHMM音声合成 (2007)
  • Author(s): 才野 慶二郎, 全 柄河, 南角 吉彦, 李 晃伸, 徳田 恵一
  • Organizer: 日本音響学会2007年秋季研究発表会
  • Place of Presentation: 山梨大学
  • Year and Date: 2007-09-21
• [Presentation] MEL-LSPを用いたHMM音声合成におけるポストフィルタリングの検討 (2007)
  • Author(s): 大浦 圭一郎, 全 柄河, 南角 吉彦, 李 晃伸, 徳田 恵一
  • Organizer: 日本音響学会2007年秋季研究発表会
  • Place of Presentation: 山梨大学
  • Year and Date: 2007-09-21
• [Presentation] Evaluation of parameter optimization methods for millimum generation error based HMM training (2007)
  • Author(s): Yi-Jian Wu, Heiga Zen, 「Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: 日本音響学会2007年秋季研究発表会
  • Place of Presentation: 山梨大学
  • Year and Date: 2007-09-21
• [Presentation] モデル鵬尤線形回腿つぐトラジェクトリmmの話櫛 (2007)
  • Author(s): 全 柄河, 南角 吉彦, 徳田 恵一
  • Organizer: 日本音響学会2007年秋季研究発表会
  • Place of Presentation: 山梨大学
  • Year and Date: 2007-09-20
• [Presentation] Speaker-independent HMM-based speech synthesis system-HTS-2007 system for the Blizzard Challenge 2007 (2007)
  • Author(s): Junichi Yamagishi, Heiga Zen, Tomoki Toda, Keiichi Tokuda
  • Organizer: Proc.of Blizzard, Challenge 2007
  • Place of Presentation: Bonn,Germany
  • Year and Date: 2007-08-25
• [Presentation] HMM音声認識におけるコンテキストの加算的構造を考慮した音響モデリング (2007)
  • Author(s): 中村和寛, 全柄河, 南角吉彦, 李晃伸, 徳田恵一
  • Organizer: 日本音響学会2007年春季研究発表会
  • Place of Presentation: 日本音響学会ボスター賞(vol.I,1-P-13, 149-150)
• [Presentation] 因子分析に基づく固有声モデルを用いたHMM音声合成 (2007)
  • Author(s): 才野慶二郎, 全柄河, 南角吉彦, 李晃伸, 徳田恵一
  • Organizer: 日本音響学会2007年秋季研究発表会
  • Place of Presentation: (vol.I,3-4-8, 365-366)
• [Presentation] Acoustic modeling with contextual additive structure for HMM-based speech recognition (2007)
  • Author(s): Yoshihiko Nankaku, Kazuhiro Nakamura, Heiga Zen, Keiichi Tokuda
  • Organizer: 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing(ICASSP 2008)
  • Place of Presentation: Las Vegas,Nevada,U.S.A
• [Presentation] Model-Space MLLR for Trajectoty HMMs (2007)
  • Author(s): Heiga Zen, Yoshihiko Nankaku, Keuchi Tokuda
  • Organizer: Interspeech 2007-EUR, OSPEECH
  • Place of Presentation: Antwerp,Belguim
• [Presentation] A trainable excitation model for HMM-based speech synthesis (2007)
  • Author(s): Ranniery Maia, Tomoki Toda, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: Interspeech 2007-EUR.OSPEECH
  • Place of Presentation: Antwerp,Belguim
• [Presentation] Spectral conversion based on statistical models including time -frequency matching (2007)
  • Author(s): Yoshihiko Nankaku, Kenichi Nakamura, and Keiichi To kuda
  • Organizer: Proc.of 6th ISCA Speech Synthesis Workshop
  • Place of Presentation: Bonn,Germany
• [Presentation] An excitation model for HMM-based speech synthesis basedon residual modeling (2007)
  • Author(s): Ranniery Maia, Tomoki Toda, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
  • Organizer: Proc.of 6th ISCA Speech Synthesis Workshop
  • Place of Presentation: Bonn,Germany
• [Presentation] Improved average-voice-based speech synthesis usinggender-mixed modeling and a parameter generation algorithm considBring GV (2007)
  • Author(s): Junichi Yamagishi, Takao Kobayashi, Steve Renals, Simon King, Heiga Zen, Tomoki Toda, Keiichi Tokuda
  • Organizer: Proc.of 6th ISCA Speech Synthesis Workshop
  • Place of Presentation: Bonn,Germany
• [Presentation] The HMM-based speech synt hesis system (HTS)version 2.0 (2007)
  • Author(s): Heiga Zen, Takashi Nose, Junichi Yamagishi, Shinji Sako, Takashi Masuko, Alan W.Black, Keiichi Tokuda
  • Organizer: Proc.of 6th ISCA Speech Synthesis Workshop
  • Place of Presentation: Bonn,Germany
• [Presentation] Statistical parametric speech synthesis (2007)
  • Author(s): Alan W.Black, Heiga Zen, Keuchi Tokuda
  • Organizer: 2007 IEEE International Conference on Acoustics, Speech, and SignalProcessing(ICASSP 2007)
  • Place of Presentation: Hawaii,USA
• [Presentation] An HMM-based approach to flexible speech synthesis (2006)
  • Author(s): Keiichi Tokuda
  • Organizer: The 5th International Symposuim on Chinese Spoken Language Processing (ISCSLP 2006)
  • Place of Presentation: Kent Ridge, Singapore
• [Presentation] Hidden Markov model-based speech synthesis as a tool for constructing comunicative spoken dialog systems (2006)
  • Author(s): Keiichi Tokuda
  • Organizer: Proc. of The 4th Joint Meeting of The Acoustical Society of America and The Acoustical Society of Japan
  • Place of Presentation: Honolulu, Hawaii
• [Presentation] The trajectory HMM : Reformulating the HMM as a trajectory model (2005)
  • Author(s): Keiichi Tokuda
  • Organizer: Trajectory Models for Speech Processing, Supported by EPSRC (The Engineering and Physical Sciences Research Council, U.K.)
  • Place of Presentation: Edinburgh, U.K.
  • Year and Date: 2005-08-31
• [Presentation] トラジェクトリHMMの制約付き最尤線形回帰による話者適応 (2005)
  • Author(s): 全柄河, 南角吉彦, 徳田恵一, 村正
  • Organizer: 日本音響学会2005年秋季研究発表会講演論文集
  • Place of Presentation: 日本音響学会粟屋潔学術奨励賞(vol.I, 3-7-6, 113-114)
• [Book] 韻律と音声言語情報処理 アクセント・イントネーション・リズムの化学 (2006)
  • Author(s): 広瀬啓吉 編著, 徳田恵一 分担
  • Total Pages: 218
  • Publisher: 丸善
• [Book] "4.3HMM音声合成における統一的な韻律の制御"韻律と音声言語情報処理-アクセント・イントネーション・リズムの科学-(広瀬啓吉編著)(ISBN978-4-621-07674-3)
  • Author(s): 徳田恵一
  • Publisher: 丸善