Papers - NANKAKU Yoshihiko
-
ベクトル量子化変分オートエンコーダを用いた事前学習に基づく自動車操作信号からのドライバ状態推定
花井謙志郎, 南角吉彦, 神沼充伸
日本自動車技術会2024年秋季大会予稿集 2024.10
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
音声特徴を制御可能な潜在変数をもつHSMM構造化アテンションに基づく音声合成
藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2024年秋季研究発表会講演論文集 1063 - 1066 2024.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model Reviewed International journal
Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024) 12782 - 12786 2024.04
Language：English Publishing type：Research paper (international conference proceedings)
-
ソース・フィルタ型ニューラルボコーダにおける周期励振信号に関する考察
青原光, 法野行哉, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2024年春季研究発表会講演論文集 813 - 816 2024.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Noisy Studentによる半教師あり学習を用いた話者識別
程塚海月, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2024年春季研究発表会講演論文集 837 - 840 2024.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
V2Coder: 階層型 VAE に基づくニューラルボコーダ
藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2023年秋季研究発表会講演論文集 1051 - 1054 2023.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
基本周波数制御性を考慮したピッチ抽出器を用いたニューラルボコーダ学習法の検討
福田 至音, 法野 行哉, 橋本 佳, 南角 吉彦, 徳田 恵一
日本音響学会2023年秋季研究発表会講演論文集 1065 - 1068 2023.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
PeriodGrad: 基本周波数を制御可能な拡散確率モデルに基づくニューラルボコーダ
法野行哉, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2023年秋季研究発表会講演論文集 1045 - 1048 2023.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
基本周波数の制御性を考慮した特徴分離に基づくニューラルボコーダ構成法
佐藤鈴夏, 藤本崇人, 法野行哉, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2023年秋季研究発表会講演論文集 1061 - 1064 2023.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
リアルタイム声質変換のための骨伝導を介した自己発声音のアクティブキャンセリング
長谷川郁弥, 橋本佳, 南角吉彦, 徳田恵一, 田中由浩, 加藤昇平
日本音響学会2023年秋季研究発表会講演論文集 1291 - 1294 2023.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
55 スタイルを選択可能なテキスト音声合成のための制御インタフェースの設計
中邑草太, 藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2023年秋季研究発表会講演論文集 1141 - 1144 2023.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
出力遅延と時間伸縮変換を考慮したリアルタイム声質変換の検討
鈴木耀, 藤本崇人, 高木信二, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2023年秋季研究発表会講演論文集 1081 - 1084 2023.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Singing voice synthesis based on a musical note position-aware attention mechanism Reviewed International journal
Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023) 2023.06
Language：English Publishing type：Research paper (international conference proceedings)
-
Embedding a differentiable mel-cepstral synthesis filter to a neural speech synthesis system Reviewed International journal
Takenori Yoshimura, Shinji Takaki, Kazuhiro Nakamura, Keiichiro Oura, Yukiya Hono, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023) 2023.06
Language：English Publishing type：Research paper (international conference proceedings)
-
自己教師あり学習による特徴抽出器とcoarse-fine変換を用いた少量学習データによる歌声変換
田中琉聖, 山田淳司, 高木信二, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2023年春季研究発表会講演論文集 705 - 708 2023.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
発声タイミングのずれを考慮したフレーム駆動型アテンション機構に基づく歌声合成
西原美玖, 法野行哉, 橋本佳, 南角吉彦, 徳田恵一
音声研究会SP2022-42 122 ( 389 ) 19 - 24 2023.02
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
自発的対話を用いた潜在スタイル表現の抽出・予測に基づく音声合成
三井健太郎, 趙天雨, 沢田慶, 法野行哉, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年秋季研究発表会講演論文集 1593 - 1596 2022.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue International journal
Kentaro Mitsui, Tianyu Zhao, Kei Sawada, Yukiya Hono, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of Interspeech 2022 2328 - 2332 2022.09
Language：English Publishing type：Research paper (international conference proceedings)
-
微分可能なメルケプストラム合成フィルタを組み込んだend-to-end音声合成システムの検討
吉村建慶, 高木信二, 中村和寛, 大浦圭一郎, 法野行哉, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年秋季研究発表会講演論文集 1585 - 1588 2022.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
半教師あり学習を用いた階層化生成モデルに基づく日本語end-to-end音声合成
藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年秋季研究発表会講演論文集 1579 - 1582 2022.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Sequence-to-sequence歌声合成のための音符位置に基づくアテンション機構の検討
法野行哉, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年秋季研究発表会講演論文集 1589 - 1592 2022.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
隠れセミマルコフモデルに基づく構造化アテンションを用いた音声合成におけるパラメータ共有構造の検討
石田龍成, 藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年秋季研究発表会講演論文集 1199 - 1202 2022.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
デコーディング時の探索を考慮した系列識別学習によるEnd-to-End音声認識
白木佑弥, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年秋季研究発表会講演論文集 1141 - 1144 2022.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Sequence-to-sequence歌声合成のための発声タイミングのモデル化に関する検討
西原美玖, 法野行哉, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年秋季研究発表会講演論文集 1359 - 1362 2022.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Autoregressive variational autoencoder with a hidden semi-Markov model-based structured attention for speech synthesis Reviewed International journal
Takato Fujimoto, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2022) 7462 - 7466 2022.05
Language：English Publishing type：Research paper (international conference proceedings)
-
HSMM構造化アテンションに基づく音声合成のためのメモリ削減手法
藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年春季研究発表会講演論文集 969 - 972 2022.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
声質・声の高さ・話速を変更可能なニューラルボコーダ構成法の検討
佐々木一匡, 吉村建慶, 高木信二, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年春季研究発表会講演論文集 935 - 938 2022.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
深層学習に基づく音声合成における顔画像情報を用いたクロスモーダル話者適応
平光啓祐, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2022年春季研究発表会講演論文集 905 - 906 2022.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
非周期性指標を考慮したニューラルボコーダの学習
法野行哉, 高木信二, 橋本佳, 中村和寛, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2022年春季研究発表会講演論文集 973 - 976 2022.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
PeriodNet: A Non-Autoregressive Raw Waveform Generative Model With a Structure Separating Periodic and Aperiodic Components Reviewed International journal
Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
IEEE Access 9 137599 - 137612 2021.10
Language：English Publishing type：Research paper (scientific journal)
DOI： 10.1109/ACCESS.2021.3118033
Other Link： https://ieeexplore.ieee.org/document/9559963
-
隠れセミマルコフモデルによる構造化アテンションを用いた自己回帰型VAEに基づくsequence-to-sequence音声合成
藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2021年秋季研究発表会講演論文集 915 - 918 2021.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
発声タイミングのずれを考慮したsequence-to-sequence歌声合成
法野行哉, 加藤大誠, 橋本佳, 大浦圭一郎,南角吉彦, 徳田恵一
日本音響学会2021年秋季研究発表会講演論文集 911 - 914 2021.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
DNN歌声合成のための調子はずれ補正
法野行哉, 橋本佳, 大浦圭一郎,南角吉彦, 徳田恵一
日本音響学会2021年秋季研究発表会講演論文集 907 - 910 2021.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
因子分析に基づくHSMMを利用した構造化アテンション音声合成
高木信二, 牛田光一, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2021年秋季研究発表会講演論文集 871 - 874 2021.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System Reviewed International journal
Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
IEEE/ACM Transactions on Audio, Speech and Language Processing 29 2803 - 2815 2021.08
Language：English Publishing type：Research paper (scientific journal)
DOI： 10.1109/TASLP.2021.3104165
Other Link： https://ieeexplore.ieee.org/document/9511835
-
PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components Reviewed International journal
Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021) 6049 - 6053 2021.06
Language：English Publishing type：Research paper (international conference proceedings)
-
学習時と合成時の一貫性を考慮したVAEに基づく自己回帰型sequence-to-sequence音声合成
藤本崇人, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2021年春季研究発表会講演論文集 947 - 950 2021.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
隠れセミマルコフモデルに基づく構造化アテンションを用いたSequence-to-Sequence音声合成
角谷健太, 吉村建慶, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2021年春季研究発表会講演論文集 943 - 946 2021.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
周期・非周期成分の分離に基づくニューラルボコーダによる音声波形のモデル化の検討
法野行哉, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2021年春季研究発表会講演論文集 861 - 864 2021.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
勾配ブースティング決定木を用いた音声合成手法の検討
岩田康平, 高木信二, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2021年春季研究発表会講演論文集 813 - 814 2021.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Hierarchical multi-grained generative model for expressive speech synthesis Reviewed International journal
Yukiya Hono, KazunaTsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of Interspeech 2020 3441 - 3445 2020.10
Language：English Publishing type：Research paper (international conference proceedings)
-
感情音声合成のためのDirichlet VAE
藤本崇人, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2020年秋季研究発表会講演論文集 789 - 790 2020.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
DNNに基づく音声ボコーダにおける周期・非周期成分のモデル化の検討
法野行哉, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2020年秋季研究発表会講演論文集 759 - 760 2020.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
音声合成における敵対的生成ネットワークを用いた複数言語・複数話者モデリング
大谷眞史, 佐藤優介, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2020年秋季研究発表会講演論文集 695 - 696 2020.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
階層化多重粒度生成モデルを用いた表現豊かな音声合成
法野行哉, 坪井一菜, 沢田慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2020年秋季研究発表会講演論文集 791 - 794 2020.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Fast and high-quality singing voice synthesis system based on convolutional neural networks Reviewed International journal
Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020) 7239 - 7243 2020.05
Language：English Publishing type：Research paper (international conference proceedings)
-
Semi-supervised learning based on hierarchical generative models for end-to-end speech synthesis Reviewed International journal
Takato Fujimoto, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020) 7644 - 7648 2020.05
Language：English Publishing type：Research paper (international conference proceedings)
-
End-to-End音声合成のための階層化生成モデルに基づく半教師あり学習
藤本崇人, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2020年春季研究発表会講演論文集 1039 - 1042 2020.03
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
歌声合成におけるニューラルボコーダの比較検討
和田蒼汰, 法野行哉, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
電子情報通信学会技術研究報告 2019.12
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
公共空間におけるスピーチプライバシー保護を目的とした合成音声によるサウンドマスキングの検討
次井貴浩, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
電子情報通信学会技術研究報告 2019.12
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Impacts of input linguistic feature representation on Japanese end-to-end speech synthesis Reviewed International journal
Takato Fujimoto, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 10th ISCA Speech Synthesis Workshop (SSW10) 166 - 171 2019.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Low computational cost speech synthesis based on deep neural networks using hidden semi-Markov model structures Reviewed International journal
Motoki Shimada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 10th ISCA Speech Synthesis Workshop (SSW10) 177 - 182 2019.09
Language：English Publishing type：Research paper (international conference proceedings)
-
楽譜時間情報を用いたアテンション機構に基づく歌声合成の検討
村田舜馬, 藤本崇人, 法野行哉, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2019年秋季研究発表会講演論文集 934 - 944 2019.09
Language：Japanese Publishing type：Research paper (other academic)
-
CNNに基づく歌声合成における計算量削減の検討
中村和寛, 高木信二, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2019年秋季研究発表会講演論文集 939 - 940 2019.09
Language：Japanese Publishing type：Research paper (other academic)
-
周期・非周期信号を用いた敵対的生成ネットワークに基づくリアルタイム音声ボコーダ
大浦圭一郎, 高木信二, 中村和寛, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2019年秋季研究発表会講演論文集 997 - 998 2019.09
Language：Japanese Publishing type：Research paper (other academic)
-
Deep neural network based real-time speech vocoder with periodic and aperiodic inputs Reviewed International journal
Keiichiro Oura, Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 10th ISCA Speech Synthesis Workshop (SSW10) 13 - 18 2019.09
Language：English Publishing type：Research paper (international conference proceedings)
-
周期・非周期信号を用いたDNNに基づくリアルタイム音声ボコーダ
大浦圭一郎, 中村和寛, 橋本佳, 南角吉彦, 徳田恵一
情報処理学会研究報告 2019-SLP-127 1 - 6 2019.06
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Speaker-dependent WaveNet-based delay-free ADPCM speech coding Reviewed International journal
Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019) 7145 - 7149 2019.05
Language：English Publishing type：Research paper (international conference proceedings)
-
Singing voice synthesis based on generative adversarial networks Reviewed International journal
Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019) 6955 - 6959 2019.05
Language：English Publishing type：Research paper (international conference proceedings)
-
歌声合成における CNN に基づく音声パラメータ生成手法の検討
中村和寛, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2019年春季研究発表会講演論文集 1033 - 1034 2019.03
Language：Japanese Publishing type：Research paper (other academic)
-
敵対的生成ネットワークを用いた歌声合成の検討
法野行哉, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2019年春季研究発表会講演論文集 1039 - 1040 2019.03
Language：Japanese Publishing type：Research paper (other academic)
-
AI歌手りんな：ユーザ歌唱や楽譜を入力とする歌声合成システム
沢田慶, 坪井一菜, Xianchao Wu, Zhan Chen, 法野行哉, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2019年春季研究発表会講演論文集 1041 - 1044 2019.03
Language：Japanese Publishing type：Research paper (other academic)
-
周期・非周期信号から駆動するディープニューラルネットワークに基づく音声ボコーダ
大浦圭一郎, 中村和寛, 橋本佳, 南角吉彦, 徳田恵一
日本音響学会2019年春季研究発表会講演論文集 1049 - 1052 2019.03
Language：Japanese Publishing type：Research paper (other academic)
-
日本語End-to-End音声合成における入力言語特徴量の影響
藤本崇人, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2019年春季研究発表会講演論文集 1061 - 1062 2019.03
Language：Japanese Publishing type：Research paper (other academic)
-
隠れセミマルコフモデルの構造を用いたDNNに基づく音声合成における計算量削減手法の検討
島田基樹, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2019年春季研究発表会講演論文集 1071 - 1072 2019.03
Language：Japanese Publishing type：Research paper (other academic)
-
DNNに基づく感情音声合成のための敵対的学習の検討
角谷健太, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2019年春季研究発表会講演論文集 1359 - 1360 2019.03
Language：Japanese Publishing type：Research paper (other academic)
-
WaveNet-based zero-delay lossless speech coding Reviewed International journal
Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2018 IEEE Workshop on Spoken Language Technology 2018.12
Language：English Publishing type：Research paper (international conference proceedings)
-
Speech synthesis using WaveNet vocoder based on periodic/aperiodic decomposition Reviewed International journal
Takato Fujimoto, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of APSIPA ASC 2018 2018.11
Language：English Publishing type：Research paper (international conference proceedings)
-
Discriminative feature extraction based on sequential variational autoencoder for speaker recognition Reviewed International journal
Takenori Yoshimura, Natsumi Koike, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of APSIPA ASC 2018 2018.11
Language：English Publishing type：Research paper (international conference proceedings)
-
Recent development of the DNN-based singing voice synthesis system -- Sinsy Reviewed International journal
Yukiya Hono, Shumma Murata, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of APSIPA ASC 2018 2018.11
Language：English Publishing type：Research paper (international conference proceedings)
-
Singing voice conversion using posted waveform data on music social media Reviewed International journal
Koki Senda, Yukiya Hono, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of APSIPA ASC 2018 2018.11
Language：English Publishing type：Research paper (international conference proceedings)
-
Image recognition based on convolutional neural networks using features generated from separable lattice hidden Markov models Reviewed International journal
Takayuki Kasugai, Yoshinari Tsuzuki, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of APSIPA ASC 2018 2018.11
Language：English Publishing type：Research paper (international conference proceedings)
-
Speaker adaptation for speech synthesis based on deep neural networks using hidden semi-Markov model structures Reviewed International journal
Kento Nakao, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of APSIPA ASC 2018 2018.11
Language：English Publishing type：Research paper (international conference proceedings)
-
The NITech text-to-speech system for the Blizzard Challenge 2018 International journal
Kei Sawada, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Blizzard Challenge 2018 Workshop 2018.09
Language：English Publishing type：Research paper (international conference proceedings)
-
A Bayesian framework for image recognition based on hidden Markov eigen-image models Reviewed
Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
IEEJ Transactions on Electrical and Electronic Engineering 13 ( 9 ) 1335 - 1347 2018.09
Language：English Publishing type：Research paper (scientific journal)
DOI： 10.1002/tee.22700
-
Deep Neural Networkに基づく歌声合成システム -- Sinsy
法野行哉, 村田舜馬, 中村和寛, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会講演論文集 1099 - 1102 2018.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
公共空間におけるスマートデバイスを用いた音声入力のためのサウンドマスキングに関する検討
次井貴浩, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会講演論文集 883 - 884 2018.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Blizzard Challenge 2018のためのNITechテキスト音声合成システム
沢田慶，吉村建慶，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
日本音響学会講演論文集 1091 - 1094 2018.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
周期・非周期成分の分離に基づくWaveNetボコーダを用いた音声合成
藤本崇人，吉村建慶，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
日本音響学会講演論文集 1125 - 1126 2018.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
話者認識のためのSequential VAEに基づく特徴抽出の検討
吉村建慶，小池なつみ，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
日本音響学会講演論文集 1341 - 1344 2018.09
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Mel-Cepstrum-Based Quantization Noise Shaping Applied to Neural-Network-Based Speech Waveform Synthesis Reviewed International journal
Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
IEEE/ACM Transactions on Audio, Speech, and Language Processing 26 ( 7 ) 1173 - 1180 2018.07
Language：English Publishing type：Research paper (scientific journal)
-
時間構造を考慮したニューラルネットワークに基づく音声合成における話者適応の検討
中尾健人, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
電子情報通信学会技術研究報告 118 ( 112 ) 53 - 58 2018.06
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Statistical voice conversion based on WaveNet Reviewed International journal
Jumpei Niwa, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
2018 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2018.04
Language：English Publishing type：Research paper (international conference proceedings)
-
Image recognition based on separable lattice HMMs using a deep neural network for output probability distributions Reviewed International journal
Eiji Ichikawa, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
2018 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2018.04
Language：English Publishing type：Research paper (international conference proceedings)
-
Constructing text-to-speech systems for languages with unknown pronunciations Reviewed
Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
Acoustical Science and Technology 39 ( 2 ) 119 - 129 2018.03
Language：English Publishing type：Research paper (scientific journal)
DOI： 10.1250/ast.39.119
-
Singing voice synthesis using timing-lag model based on a deep neural network
2018.03
Language：Japanese Publishing type：Research paper (other academic)
-
Singing voice synthesis based on neural network using a structure of a hidden semi-Markov model
2018.03
Language：Japanese Publishing type：Research paper (other academic)
-
隠れマルコフモデルに基づく日本語音声合成ソフトウェア入門 Invited
大浦 圭一郎, 橋本 佳, 南角 吉彦, 徳田 恵一
システム制御情報学会誌 62 ( 2 ) 57 - 62 2018.02
Language：Japanese Publishing type：Research paper (scientific journal)
-
A study on voice conversion based on WaveNet
IEICE Technical Report 117 ( 393 ) 99 - 104 2018.01
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Trajectory training considering power for speech synthesis based on neural networks
IEICE Technical Report 117 ( 393 ) 43 - 48 2018.01
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Mel-cepstrum based quantization noise shaping applied to speech synthesis based on WaveNet
IEICE Technical Report 117 ( 393 ) 93 - 98 2018.01
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Blizzard Challenge 2017のためのNITechテキスト音声合成システム
沢田慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2017年秋季研究発表会講演論文集 287 - 290 2017.09
Language：Japanese Publishing type：Research paper (other academic)
-
音楽SNSの投稿データを利用した歌唱声質変換
法野行哉, 沢田慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一, 近藤大介, 石川大輔
日本音響学会2017年秋季研究発表会講演論文集 209 - 210 2017.09
Language：Japanese Publishing type：Research paper (other academic)
-
WaveNet-based voice conversion
Jumpei Niwa, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
日本音響学会2017年秋季研究発表会講演論文集 207 - 208 2017.09
Language：English Publishing type：Research paper (other academic)
-
WaveNetにおけるメルケプストラムに基づくノイズシェーピング量子化法の適用
吉村建慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2017年秋季研究発表会講演論文集 193 - 194 2017.09
Language：Japanese Publishing type：Research paper (other academic)
-
Simultaneous optimization of multiple tree-based factor analyzed HMM for speech synthesis Reviewed
Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
IEEE/ACM Transactions on Audio, Speech and Language Processing 25 ( 9 ) 1532 - 1541 2017.09
Language：English Publishing type：Research paper (scientific journal)
-
Articulatory text-to-speech synthesis using the digital waveguide mesh driven by a deep neural network Reviewed International coauthorship
Amelia Gully, Takenori Yoshimura, Damian Murphy, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of Interspeech 2017 234 - 238 2017.08
Language：English Publishing type：Research paper (international conference proceedings)
-
Image recognition based on discriminative models using features generated from separable lattice HMMs Reviewed
Yoshinari Tsuzuki, Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2017) 2607 - 2611 2017.03
Language：English Publishing type：Research paper (international conference proceedings)
-
ニューラルネットワークに基づく音声合成における音響特徴量抽出条件の検討
村瀬栞, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2017年春季研究発表会講演論文集 263 - 264 2017.03
Language：Japanese Publishing type：Research paper (other academic)
-
DNN-GMMハイブリッドモデルに基づく声質変換の検討
市川裕詞, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2017年春季研究発表会講演論文集 233 - 234 2017.03
Language：Japanese Publishing type：Research paper (other academic)
-
DNN音声合成における音響特徴量系列とその時間構造の同時モデル化
橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
電子情報通信学会技術研究報告 116 ( 414 ) 71 - 76 2017.01
Language：Japanese Publishing type：Research paper (other academic)
-
オーディオブックを用いた表現豊かな音声合成のための言語特徴量の検討
浅井千明, 沢田慶, 橋本佳, 大浦圭一郎, 南角吉彦, 徳田恵一
電子情報通信学会技術研究報告 116 ( 414 ) 35 - 40 2017.01
Language：Japanese Publishing type：Research paper (other academic)
-
A Bayesian Approach to Image Recognition Based on Separable Lattice Hidden Markov Models Reviewed
Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
IEICE TRANSACTIONS on Information and Systems E99-D ( 12 ) 3119 - 3131 2016.12
Language：English Publishing type：Research paper (scientific journal)
-
Temporal modeling in neural network based statistical parametric speech synthesis Reviewed International journal
Keiichi Tokuda, Kei Hashimoto, Keiichiro Oura, and Yoshihiko Nankaku
9th ISCA Speech Synthesis Workshop 113 - 118 2016.09
Authorship：Lead author Language：English Publishing type：Research paper (international conference proceedings)
-
Redefining the linguistic context feature set for HMM and DNN TTS through position and parsing Reviewed International coauthorship International journal
Rasmus Dall, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Interspeech 2016 2851 - 2855 2016.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Singing voice synthesis based on deep neural networks Reviewed International journal
Masanari Nishimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Interspeech 2016 2478 - 2482 2016.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Voice conversion based on trajectory model training of neural networks considering global variance Reviewed International journal
Naoki Hosaka, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Interspeech 2016 307 - 311 2016.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Image recognition based on discriminative models using features extracted from separable lattice HMMs
116 ( 89 ) 7 - 12 2016.06
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Trajectory training considering global variance for speech synthesis based on neural networks Reviewed International journal
Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016) 2016.03
Language：English Publishing type：Research paper (international conference proceedings)
-
Deep Neural Networkに基づく歌声合成の検討
西村 方成，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2016.03
Language：Japanese Publishing type：Research paper (other academic)
-
条件付確率場に基づく音声の基本周波数推定の検討
鈴木 達也，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2016.03
Language：Japanese Publishing type：Research paper (other academic)
-
楽譜情報に基づく事前分布を用いたHMM歌声合成の検討
大浦 圭一郎，橋本 佳，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2016.03
Language：Japanese Publishing type：Research paper (other academic)
-
ニューラルネットワークに基づく声質変換における系列内変動を考慮したトラジェクトリ学習
保坂 尚紀，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2016.03
Language：Japanese Publishing type：Research paper (other academic)
-
クラウドソーシングによる音声収集のための収録ソフトウェアの設計
吉村 建慶，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2016.03
Language：Japanese Publishing type：Research paper (other academic)
-
統計的パラメトリック音声合成のためのオーディオブックを用いた学習コーパス自動構築
沢田 慶，伊神 和輝，浅井 千明，佐藤 雄介，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2016.03
Language：Japanese Publishing type：Research paper (other academic)
-
画像認識のための混合出力分布を用いた分離型格子HMMにおけるパラメータ共有構造の検討
助川正人，沢田 慶，橋本 佳，南角吉彦，徳田恵一
電子情報通信学会技術研究報告 2016.02
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
発音情報が未知の言語におけるテキスト音声合成システム構築法の評価
沢田 慶，橋本 佳，大浦圭一郎，南角吉彦，徳田恵一
電子情報通信学会技術研究報告 2015.12
Language：Japanese Publishing type：Research paper (conference, symposium, etc.)
-
Prosodically-Enhanced Recurrent Neural Network Language Models Reviewed International coauthorship International journal
Siva Reddy Gangireddy, Steve Renals, Yoshihiko Nankaku, Akinobu Lee
Proceedings of Interspeech 2015 2015.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Simultaneous Optimization of Multiple Tree Structures for Factor Analyzed HMM-Based Speech Synthesis Reviewed International journal
Takenori Yoshimura, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of Interspeech 2015 2015.09
Language：English Publishing type：Research paper (international conference proceedings)
-
複数の音響特徴量を用いた対数線形モデルに基づく話者認識の検討
橋本 聖矢，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2015.09
Language：Japanese Publishing type：Research paper (other academic)
-
ニューラルネットワークに基づく音声合成における系列内変動を考慮したトラジェクトリモデル学習
橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2015.09
Language：Japanese Publishing type：Research paper (other academic)
-
音声の高帯域成分復元を考慮したメルケプストラム分析に基づくHMM音声合成の検討
中村 和寛，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2015.09
Language：Japanese Publishing type：Research paper (other academic)
-
発音情報が未知の言語におけるテキスト音声合成システム構築法の検討
沢田 慶，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会研究発表会論文集 2015.09
Language：Japanese Publishing type：Research paper (other academic)
-
The Effect of Neural Networks in Statistical Parametric Speech Synthesis Reviewed International journal
Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2015) 2015.04
Language：English Publishing type：Research paper (international conference proceedings)
-
HMM歌声合成における音声データの誤りに頑健なモデル化手法の検討
虫鹿弘二，中村和寛，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
情報処理学会研究報告 2015-MUS-106 ( 13 ) 1 - 6 2015.03
Language：Japanese Publishing type：Research paper (other academic)
-
隠れマルコフモデルに基づく英語歌声合成 Reviewed
中村和寛, 大浦圭一郎, 南角吉彦, 徳田恵一
電子情報通信学会論文誌 J97-D ( 11 ) 1572 - 1581 2014.11
Language：Japanese Publishing type：Research paper (scientific journal)
-
H/L型アクセント推定と音響モデリングを統合したHMM音声合成の検討
神谷翔大，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
日本音響学会秋季研究発表会講演論文集 237 - 238 2014.09
Language：Japanese Publishing type：Research paper (other academic)
-
因子分析に基づくHMM音声合成における基底クラスタリングの検討
吉村建慶，橋本佳，南角吉彦，徳田恵一
日本音響学会秋季研究発表会講演論文集 239 - 240 2014.09
Language：Japanese Publishing type：Research paper (other academic)
-
ニューラルネットワークに基づく音声合成における生成モデルの利用の検討
橋本佳，大浦圭一郎，南角吉彦，徳田恵一
日本音響学会秋季研究発表会講演論文集 245 - 246 2014.09
Language：Japanese Publishing type：Research paper (other academic)
-
統計的機械学習問題としての音声研究
南角吉彦
電子情報通信学会技術研究報告 SP2014-67-114 ( 151 ) 25 - 30 2014.07
Language：Japanese Publishing type：Research paper (other academic)
-
Image recognition based on separable lattice trajectory 2-D HMM Reviewed
Akira Tamamori, Yoshihiko Nankaku, and Keiichi Tokuda
IEICE Transactions E97-D ( 7 ) 1842 - 1854 2014.07
Language：English Publishing type：Research paper (scientific journal)
-
Automatic Driver Characteristics Estimation Using Driving Signals Reviewed
Atsunobu Kaminuma, Yoshihiko Nankaku
1 - 9 2014.06
Language：English Publishing type：Research paper (international conference proceedings)
-
Integration of spectral feature extraction and modeling for HMM-based speech synthesis Reviewed
Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
IEICE Transactions E97-D ( 6 ) 1438 - 1448 2014.06
Language：English Publishing type：Research paper (scientific journal)
-
Integration of speaker and pitch adaptive training for HMM-based singing voice synthesis Reviewed
Kanako Shirota, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2014) 2578 - 2582 2014.05
Language：English Publishing type：Research paper (international conference proceedings)
-
HMM-based singing voice synthesis and its application to Japanese and English Reviewed
Kazuhiro Nakamura, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2014) 265 - 269 2014.05
Language：English Publishing type：Research paper (international conference proceedings)
-
Spectral modeling with contextual additive structure for HMM-based speech synthesis Reviewed
Shinji Takaki, Yoshihiko Nankaku and Keiichi Tokuda
IEEE Transactions on Audio, Speech, and Language Processing 8 ( 2 ) 229 - 238 2014.04
Language：English Publishing type：Research paper (scientific journal)
-
統計的音声対話システムにおける登録キーワードの近傍単語を優先した仮説生成に基づく応答選択
小升 章裕，李 晃伸，南角 吉彦，徳田 恵一
音響学会公演論文集 221 - 224 2014.03
Language：Japanese Publishing type：Research paper (scientific journal)
-
状態レベルのコンテキストを用いたHMM音声合成の検討
大浦 圭一郎，橋本 佳，南角 吉彦，徳田 恵一
音響学会公演論文集 341 - 342 2014.03
Language：Japanese Publishing type：Research paper (scientific journal)
-
低周波数標本化音声データの高帯域成分復元を考慮したメルケプストラム分析の検討
中村 和寛，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
音響学会公演論文集 339 - 340 2014.03
Language：Japanese Publishing type：Research paper (scientific journal)
-
HMM音声合成におけるLSPに関連した特徴量表現の検討
有竹 貴士，中村 和寛，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
音響学会公演論文集 337 - 338 2014.03
Language：Japanese Publishing type：Research paper (scientific journal)
-
HMM歌声合成における音声データの誤りに頑健なモデル学習手法の検討
虫鹿 弘二，中村 和寛，橋本 佳 ，大浦 圭一郎，南角 吉彦，徳田 恵一
音響学会公演論文集 335 - 336 2014.03
Language：Japanese Publishing type：Research paper (scientific journal)
-
GMM事後確率に基づいた重み付き変換関数による声質変換の検討
鶴野 高輝，橋本 佳 ，南角 吉彦，徳田 恵一
音響学会公演論文集 327 - 328 2014.03
Language：Japanese Publishing type：Research paper (scientific journal)
-
表現語空間を用いた連結固有声法に基づくクロスリンガル話者適応の検討
佐藤 雄介，中村 和寛，橋本 佳，大浦 圭一郎，南角 吉彦，徳田 恵一
音響学会公演論文集 325 - 326 2014.03
Language：Japanese Publishing type：Research paper (scientific journal)
-
条件付き確率場に基づく仮説の逐次早期確定を用いた低遅延音声インタフェース
伊神 陽介，李 晃伸，徳田 恵一，南角 吉彦
音響学会公演論文集 63 - 64 2014.03
Language：Japanese Publishing type：Research paper (scientific journal)
-
変分ベイズ法による特徴量生成を用いた対数線形モデルに基づく話者 認識
柘植彬史，橋本佳，南角吉彦，徳田恵一
電子情報通信学会技術研究報告 113 ( 404 ) 13 - 18 2014.01
Language：Japanese Publishing type：Research paper (scientific journal)
-
Image recognition based on hidden Markov eigen-image models using variational Bayesian method Reviewed
Kei Sawada, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
Proc. of APSIPA 2013 2013.10
Language：English Publishing type：Research paper (scientific journal)
-
運転信号を用いたドライバ行動および個人特性の自動推定
神沼 充伸，南角 吉彦
自動車技術会 学術講演会前刷集, ( 128-13 ) 1 - 7 2013.10
Language：Japanese Publishing type：Research paper (scientific journal)
-
ユーザ生成型音声対話コンテンツに向けた有限状態トランスデューサに基づく簡潔な対話記述法の検討
船谷内 泰斗，大浦 圭一郎，南角 吉彦，李 晃伸，徳田 恵一
音響学会公演論文集 223 - 224 2013.09
Language：Japanese Publishing type：Research paper (scientific journal)
-
ベイズ統計量を用いた対数線形モデルに基づく話者認識
柘植 彬史，橋本 佳，南角 吉彦，徳田 恵一
音響学会公演論文集 73 - 74 2013.09
Language：Japanese Publishing type：Research paper (scientific journal)
-
HMMに基づく英語歌声合成の検討
中村 和寛，大浦 圭一郎，南角 吉彦，徳田 恵一
音響学会公演論文集 299 - 300 2013.09
Language：Japanese Publishing type：Research paper (scientific journal)
-
Cross-lingual speaker adaptation based on factor analysis using bilingual speech data for HMM-based speech synthesis Reviewed
Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku and Keiichi Tokuda
Proc. of ISCA Speech Synthesis Workshop(SSW8), 297 - 302 2013.08
Language：English Publishing type：Research paper (scientific journal)
-
Separable lattice 2-D HMMs introducing state duration control for recognition of images with various variations Reviewed
Takaya Makino, Shinji Takaki, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013) 3203 - 3207 2013.05
Language：English Publishing type：Research paper (scientific journal)
-
Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis Reviewed
Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013) 7883 - 7887 2013.05
Language：English Publishing type：Research paper (scientific journal)
-
Contextual partial additive structure for HMM-based speech synthesis Reviewed
Shinji Takaki, Yoshihiko Nankaku and Keiichi Tokuda
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013) 7878 - 7882 2013.05
Language：English Publishing type：Research paper (scientific journal)
-
Image recognition based on separable lattice trajectory 2-d HMMs Reviewed
Akira Tamamori, Yoshihiko Nankaku, Keiichi Tokuda
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013) 3467 - 3471 2013.05
Language：English Publishing type：Research paper (scientific journal)
-
A Bayesian framework using multiple model structures for speech recognition Reviewed
IEICE Transactions on Information and Systems 2013.04
Language：English Publishing type：Research paper (scientific journal)
-
HMM歌声合成における歌唱者適応学習の検討
城田佳菜子, 中村和寛, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2013年春期研究発表会予稿集 I 339 - 340 2013.03
Language：Japanese Publishing type：Research paper (other academic)
-
HMM音声合成のためのバイリンガルデータを用いた因子分析に基づくクロスリンガル話者適応
吉村建慶，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
日本音響学会2013年春期研究発表会予稿集 I 267 - 268 2013.03
Language：Japanese Publishing type：Research paper (other academic)
-
Cross-lingual speaker adaptation for HMM-based speech synthesis using joint-eigenvoices with a space of perceptual characteristics
Viviane de Franca Oliveira, Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
日本音響学会2013年春期研究発表会予稿集 I 269 - 270 2013.03
Language：English Publishing type：Research paper (other academic)
-
HMM音声合成におけるメルケ プストラム分析を統合した音響モデリングの検討
中村和寛，橋本佳，南角吉彦，徳田恵一
日本音響学会2013年春期研究発表会予稿集 I 289 - 290 2013.03
Language：Japanese Publishing type：Research paper (other academic)
-
HMM音声合成における因子分析を用いた発話適応学習の検討
桑子修一，高木信二，橋本佳，南角吉彦，徳田恵一
日本音響学会2013年春期研究発表会予稿集 I 291 - 292 2013.03
Language：Japanese Publishing type：Research paper (other academic)
-
音高正規化学習を用いたHMM歌声合成における調子外れの補正
喜多村翔斗，中村和寛，橋本佳，大浦圭一郎，南角吉彦，徳田恵一
日本音響学会2013年春期研究発表会予稿集 I 337 - 338 2013.03
Language：Japanese Publishing type：Research paper (other academic)
-
HMM音声合成におけるF0/有声・無声重みの個別クラスタリングによる 合成音声の評価
岡田 知大，高木 信二，南角 吉彦，徳田 恵一
日本音響学会2013年春期研究発表会予稿集 I 293 - 294 2013.03
Language：Japanese Publishing type：Research paper (other academic)
-
変分ベイズ法を用いた可変固 有画像モデルに基づく画像認識
沢田慶，橋本佳，南角吉彦，徳田恵一
電子情報通信学会技術研究報告 112 ( 441 ) 155 - 160 2013.02
Language：Japanese Publishing type：Research paper (other academic)
-
状態継続長制 御に基づいた拡張分離型格子HMMによる変動に頑健な画像認識
牧野貴也，高木信二，橋本佳，南角吉彦，徳田恵一
電子情報通信学会技術研究報告 112 ( 441 ) 149 - 154 2013.02
Language：Japanese Publishing type：Research paper (other academic)
-
Cross-lingual speaker adaptation for HMM-based speech synthesis based on perceptual characteristics and spaker interpolation Reviewed
Proceedings of Interspeech 2012 2012.09
Language：English Publishing type：Research paper (international conference proceedings)
-
A Bayesian approach to speaker recognition based on GMMs using multiple model structures Reviewed
Proceedings of Interspeech 2012 2012.09
Language：English Publishing type：Research paper (international conference proceedings)
-
ドライバの社会性に関するCharacter自動推定
神沼 充伸, 西崎 友規子, ブエ・ステファン, 南角 吉彦, 李 晃伸
Human Interface 2012予稿集 2012.09
Language：Japanese Publishing type：Research paper (other academic)
-
HMM音声合成のための加算モデ ル構造に基づく複数話者同時モデリングの検討
高木 信二，南角 吉彦，徳田 恵一
日本音響学会2012年秋期研究発表会予稿集 I 281 - 281 2012.09
Language：Japanese Publishing type：Research paper (other academic)
-
HMM歌声合成における状態数可変のモデル構造の検討
大浦 圭一郎，南角 吉彦，徳田 恵一
日本音響学会2012年秋期研究発表会予稿集 I 275 - 276 2012.09
Language：Japanese Publishing type：Research paper (other academic)
-
隠れ条件付確率場を用いた音声 認識のためのアニーリングに基づく学習アルゴリズムの検討
真野 翔平，南角 吉彦，徳田 恵一
日本音響学会2012年秋期研究発表会予稿集 I 79 - 80 2012.09
Language：Japanese Publishing type：Research paper (other academic)
-
複数のモデル構造を用 いた変分ベイズ法に基づく話者認識
服部 貴文，橋本 佳，南角 吉彦，徳田 恵一
日本音響学会2012年秋期研究発表会予稿集 I 39 - 40 2012.09
Language：Japanese Publishing type：Research paper (other academic)
-
An extension of separable lattice 2-D HMMs for rotational data variations Reviewed
IEICE Transactions on Information and Systems E95-D ( 8 ) 2074 - 2083 2012.08
Language：English Publishing type：Research paper (scientific journal)
-
登録キーワード と汎用言語モデルを用いた音声認識部・応答選択部の密結合に基づく統 計的音声対話システム
平野隆司，加藤杏樹，南角吉彦，李晃伸，徳田恵一
音声言語情報処理研究発表会 2012-SLP-92 ( 6 ) 1 - 6 2012.07
Language：Japanese Publishing type：Research paper (other academic)
-
Face Recognition Based on Separable Lattice 2-D HMMs Using Variational Bayesian Method Reviewed
Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012) 2205 - 2208 2012.03
Language：English Publishing type：Research paper (international conference proceedings)
-
Face Recognition Based on Extended Separable Lattice 2-D HMMs Reviewed
Keisuke Kumaki, Yoshihiko Nankaku, and Keiichi Tokuda
Proceedings of 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012) 2209 - 2212 2012.03
Language：English Publishing type：Research paper (international conference proceedings)
-
Pitch adaptive training for HMM-based singing voice synthesis Reviewed
Keiichiro Oura, Ayami Mase, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012) 5377 - 5380 2012.03
Language：English Publishing type：Research paper (international conference proceedings)
-
A model structure integration based on a Bayesian framework for speech recognition Reviewed
Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012) 4813 - 4816 2012.03
Language：English Publishing type：Research paper (international conference proceedings)
-
Product of Experts for Statistical Parametric Speech Synthesis Reviewed
Heiga Zen, Mark J. F. Gales, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011) 20 ( 3 ) 794 - 805 2012.03
Language：English Publishing type：Research paper (scientific journal)
-
Cross-lingual speaker adaptation for HMM-based speech synthesis using speaker interpolation based on perceptual characteristics
Viviane de F. Oliveira, Sayaka Shiota, Yoshihiko Nankaku, Keiichi Tokuda
日本音響学会2012年春季研究発表会論文集 405 - 406 2012.03
Language：English Publishing type：Research paper (other academic)
-
変分ベイズ法を用いた分離型2次元格子HMMの学習におけるアニーリング制御の適用
沢田慶，玉森聡，橋本佳，南角吉彦，徳田 恵一
情報処理学会誌 2 409 - 410 2012.03
Language：Japanese Publishing type：Research paper (other academic)
-
コンテキストの部分的な加算構造に基づくHMM音声合成
高木信二, 南角吉彦, 徳田恵一
日本音響学会2012年春季研究発表会論文集 303 - 304 2012.03
Language：Japanese Publishing type：Research paper (other academic)
-
HMM歌声合成における音高正規化学習の検討
大浦圭一郎, 間瀬絢美, 南角吉彦, 徳田恵一
Technical Report of IPSJ 1 - 6 2012.02
Language：Japanese Publishing type：Research paper (other academic)
-
Speech recognition based on statistical models including multiple phonetic decision trees Reviewed
Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
Acoustical Science and Technology 32 ( 6 ) 236 - 243 2011.11
Language：English Publishing type：Research paper (international conference proceedings)
-
Speech recognition based on statistical models including multiple phonetic decision trees Reviewed
Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
Acoustical Science and Technology 32 ( 6 ) 236 - 243 2011.11
Language：English Publishing type：Research paper (scientific journal)
-
分離型格子HMMの構造を用いた隠れ条件付確率場に基づく顔画像認識
熊木慶介，南角吉彦，徳田恵一
電子情報通信学会技術研究報告 111 ( 317 ) 131 - 136 2011.11
Language：Japanese Publishing type：Research paper (other academic)
-
変分ベイズ法を用いた分離型2次元格子HMMに基づく顔画像認識
沢田慶，玉森聡，橋本佳，南角 吉彦，徳田恵一
電子情報通信学会技術研究報告 111 ( 317 ) 125 - 130 2011.11
Language：Japanese Publishing type：Research paper (other academic)
-
音高正規化学習を用いたHMM歌声合成の検討
間瀬絢美, 大浦圭一郎, 南角吉彦, 徳田恵一
日本音響学会2011年秋季研究発表会論文集 283 - 284 2011.09
Language：Japanese Publishing type：Research paper (other academic)
-
ベイズ音声合成における事前分布とモデル構造の話者間共有
橋本佳, 南角吉彦, 徳田恵一
日本音響学会2011年秋季研究発表会論文集 345 - 348 2011.09
Language：Japanese Publishing type：Research paper (other academic)
-
連続音声認識における仮説の低遅延逐次確定アルゴリズムの評価
大野博之, 南角吉彦, 李晃伸, 徳田恵一
日本音響学会2011年秋季研究発表会論文集 45 - 46 2011.09
Language：Japanese Publishing type：Research paper (other academic)
-
Multi-Speaker Modeling with Shared Prior Distributions and Model Structures for Bayesian Speech Synthesis Reviewed
Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of Interspeech 2011 113 - 116 2011.08
Language：English Publishing type：Research paper (international conference proceedings)
-
A Bayesian Approach to Voice Conversion Based on GMMs Using Multiple Model Structures Reviewed
Lei Li, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of Interspeech 2011 661 - 664 2011.08
Language：English Publishing type：Research paper (international conference proceedings)
-
GMM-based missing-feature reconstruction on multi-frame windows Reviewed
Ulpu Remes, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of Interspeech 2011 1665 - 1668 2011.08
Language：English Publishing type：Research paper (international conference proceedings)
-
Estimation of Window Coefficients for Dynamic Feature Extraction for HMM-based Speech Synthesis Reviewed
Ling-Hui Chen, Yoshihiko Nankaku, Heiga Zen, Keiichi Tokuda, Zhen-Hua Ling, Li-Rong Dai
Proceedings of Interspeech 2011 1801 - 1804 2011.08
Language：English Publishing type：Research paper (international conference proceedings)
-
Evaluation of Tree-trellis based Decoding in Over-million LVCSR Reviewed
Naoaki Ito, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
Proceedings of Interspeech 2011 1937 - 1940 2011.08
Language：English Publishing type：Research paper (international conference proceedings)
-
モデル構造の統合手法を用いたベイズ基準による音声認識
塩田さやか, 橋本佳, 南角吉彦, 徳田恵一
Technical Report of IEICE 11 - 16 2011.06
Language：Japanese Publishing type：Research paper (other academic)
-
An optimization algorithm of mean and variance parameter tying structures for HMM-based speech synthesis Reviewed
Shinji Takaki, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011) 4700 - 4703 2011.05
Language：English Publishing type：Research paper (international conference proceedings)
-
Global variance modeling on frequency domain delta LSP for HMM-based speech synthesis Reviewed
Shifeng Pan, Yoshihiko Nankaku, Keiichi Tokuda, Jianhua Tao
Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011) 4716 - 4719 2011.05
Language：English Publishing type：Research paper (international conference proceedings)
-
Bayesian context clustering using cross validation for speech recognition Reviewed
Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
IEICE TRANSACTIONS on Information & Systems E94-D ( 3 ) 668 - 678 2011.03
Language：English Publishing type：Research paper (scientific journal)
-
Continuous Stochastic Feature Mapping Based on Trajectory HMMs Reviewed
Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
IEEE Transactions on Audio, Speech, and Language Processing 18 ( 5 ) 417 - 430 2011.02
Language：English Publishing type：Research paper (scientific journal)
-
A Frame-Based Context-Dependent Acoustic Modeling for Speech Recognition Reviewed
Ryuta Terashima, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda
130 ( 10 ) 1856 - 1864 2010.11
Language：Japanese Publishing type：Research paper (scientific journal)
-
Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthesis Considering Differences Between Language-Dependent Average Voices Reviewed
Xianglin Peng, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
Proc. of IEEE 10th International Conference on Signal Processing 605 - 608 2010.10
Language：English Publishing type：Research paper (international conference proceedings)
-
HMM-based singing voice synthesis system using pitch-shifted pseudo training data Reviewed
Ayami Mase, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
Proc. of Interspeech 2010 845 - 848 2010.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Speaker Adaptation Based on Nonlinear Spectral Transform for Speech Recognition Reviewed
Toyohiro Hayashi, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
Proc. of Interspeech 2010 542 - 545 2010.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Spectral modeling with contextual additive structure for HMM-based speech synthesis Reviewed
Shinji Takaki, Yoshihiko Nankaku, and Keiichi Tokuda
Proc. of 7th ISCA Speech Synthesis Workshop 100 - 105 2010.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Bayesian speech synthesis framework integrating training and synthesis processes Reviewed
Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda
Proc. of 7th ISCA Speech Synthesis Workshop 106 - 111 2010.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Recent Development of the HMM-based Singing Voice Synthesis System -- Sinsy Reviewed
Keiichiro Oura, Ayami Mase, Tomohiko Yamada, Satoru Muto, Yoshihiko Nankaku, and Keiichi Tokuda
Proc. of 7th ISCA Speech Synthesis Workshop 211 - 216 2010.09
Language：English Publishing type：Research paper (international conference proceedings)
-
Voice activity detection based on conditional random fields using multiple features Reviewed
Akira Saito, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
Proc. of Interspeech 2010 2086 - 2089 2010.09
Language：English Publishing type：Research paper (international conference proceedings)
-
FACE RECOGNITION BASED ON SEPARABLE LATTICE 2-D HMM WITH STATE DURATION MODELING Reviewed
Yoshiaki Takahashi, Akira Tamamori, Yoshihiko Nankaku, Keiichi Tokuda
2010 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010) 2162 - 2165 2010.03
Language：English Publishing type：Research paper (international conference proceedings)
-
AN EXTENSION OF SEPARABLE LATTICE 2-D HMMS FOR ROTATIONAL DATA VARIATIONS Reviewed
Akira Tamamori, Yoshihiko Nankaku, Keiichi Tokuda
2010 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010) 2206 - 2209 2010.03
Language：English Publishing type：Research paper (international conference proceedings)
-
Factor analyzed voice models for HMM-based speech synthesis Reviewed
Kyosuke Kazumi, Yoshihiko Nankaku, Keiichi Tokuda
2010 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010) 4234 - 4237 2010.03
Language：English Publishing type：Research paper (international conference proceedings)
-
STATISTICAL PARAMETRIC SPEECH SYNTHESIS BASED ON PRODUCT OF EXPERTS Reviewed
Heiga Zen, Mark J. F. Gales, Yoshihiko Nankaku, Keiichi Tokuda
2010 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2010) 4242 - 4245 2010.03
Language：English Publishing type：Research paper (international conference proceedings)
-
A covariance-tying technique for HMM-based speech synthesis Reviewed
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda
IEICE Transactions on Information Systems E93-D ( 3 ) 2010.03
Language：English Publishing type：Research paper (scientific journal)
-
音声認識のための非線形スペクトル変換を用いた話者適応
林 豊大, 南角 吉彦, 李 晃伸, 徳田 恵一
電子情報通信学会技術研究報告 109 ( 356 ) 1 - 6 2009.12
Language：Japanese Publishing type：Research paper (other academic)
-
ユーザ生成型音声対話コンテンツを用いた音声情報案内システム
福田 敏則, 吉見 孔孝, 南角 吉彦, 李 晃伸, 徳田 恵一
電子情報通信学会技術研究報告 109 ( 356 ) 207 - 212 2009.12
Language：Japanese Publishing type：Research paper (other academic)
-
多様な声質を表現するための因子分析モデルに基づくHMM音声合成
鹿住 恭介, 南角 吉彦, 徳田 恵一
電子情報通信学会技術研究報告 109 ( 356 ) 177 - 182 2009.12
Language：Japanese Publishing type：Research paper (other academic)
-
音声対話システムのためのN-gramに基づくキーワードからの文生成
吉見 孔孝, 南角 吉彦, 李 晃伸, 徳田 恵一
電子情報通信学会技術研究報告 109 ( 356 ) 71 - 76 2009.12
Language：Japanese Publishing type：Research paper (other academic)
-
複数の特徴量による条件付確率場に基づく音声区間検出
斎藤 彰, 南角 吉彦, 李 晃伸, 徳田 恵一
電子情報通信学会技術研究報告 109 ( 356 ) 59 - 64 2009.12
Language：Japanese Publishing type：Research paper (other academic)
-
HMM歌声合成システムのためのビブラートモデルの導入
山田 知彦，武藤 聡，南角 吉彦，酒向 慎司，徳田 恵一
日本音響学会2009年秋期研究発表会予稿集 I 309 - 312 2009.09
Language：Japanese Publishing type：Research paper (other academic)
-
バイモーダル音声認識における特徴量重みの動的決定法に関する検討
岩島 匡秋，南角 吉彦，李 晃伸，徳田 恵一
日本音響学会2009年秋期研究発表会予稿集 I 81 - 82 2009.09
Language：Japanese Publishing type：Research paper (other academic)
-
ユーザ生成型音声対話コンテンツに基づく音声情報案内システムの構築
福田 敏則，吉見 孔孝，南角 吉彦，李 晃伸，徳田 恵一
日本音響学会2009年秋期研究発表会予稿集 I 81 - 82 2009.09
Language：Japanese Publishing type：Research paper (other academic)
-
音声対話システムのためのN-gramに基づくキーワードを制約とする文 生成手法の検討
吉見 孔孝，南角 吉彦，李 晃伸，徳田 恵一
日本音響学会2009年秋期研究発表会予稿集 I 209 - 210 2009.09
Language：Japanese Publishing type：Research paper (other academic)
-
ベイズ基準によるHSMM音声合成の評価
橋本 佳，南角 吉彦，徳田 恵一
日本音響学会2009年秋期研究発表会予稿集 I 257 - 258 2009.09
Language：Japanese Publishing type：Research paper (other academic)
-
複数の特徴量を用いた条件付確率場に基づく音声区間検出
斎藤 彰，南角 吉彦，李 晃伸，徳田 恵一
日本音響学会2009年秋期研究発表会予稿集 I 47 - 48 2009.09
Language：Japanese Publishing type：Research paper (other academic)
-
音声認識のための非線形スペクトル変換に基づく話者適応
林 豊大，南角 吉彦，李 晃伸，徳田 恵一
日本音響学会2009年秋期研究発表会予稿集 I 19 - 20 2009.09
Language：Japanese Publishing type：Research paper (other academic)
-
Training Algorithm Based on Deterministic Annealing for Bayesian Speech Recognition
I 3 - 6 2009.09
Language：English Publishing type：Research paper (other academic)
-
Tying Covariance Matrices to Reduce the Footprint of HMM-Based Speech Synthesis Systems Reviewed
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
Proceedings of Interspeech 2009 2009.09
Language：English Publishing type：Research paper (other academic)
-
A Bayesian Approach to Hidden Semi-Markov Model Based Speech Synthesis Reviewed
Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of Interspeech 2009 2009.09
Language：English Publishing type：Research paper (other academic)
-
Deterministic Annealing Based Training Algorithm for Bayesian Speech Recognition Reviewed
Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of Interspeech 2009 2009.09
Language：English Publishing type：Research paper (other academic)
-
State Mapping Based Method for Cross-Lingual Speaker Adaptation in HMM-Based Speech Synthesis Reviewed
Yi-Jian Wu, Yoshihiko Nankaku, Keiichi Tokuda
Proceedings of Interspeech 2009 528 - 531 2009.09
Language：English Publishing type：Research paper (other academic)
-
Stereo-based stochastic noise compensation based on trajectory GMMs Reviewed
Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda,
Proceedings of 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009) 4577 - 4580 2009.04
Language：English Publishing type：Research paper (other academic)
-
Voice conversion based on simultaneous modeling of spectrum and F0 Reviewed
Kaori Yutani, Yosuke Uto, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
Proceedings of 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009) 3897 - 3900 2009.04
Language：English Publishing type：Research paper (other academic)
-
A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System Reviewed
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
IEICE Transactions on Information Systems E91-D ( 3 ) 2693 - 2700 2007.11
Language：English Publishing type：Research paper (scientific journal)
-
WFSTを用いたHSMM音声認識
大浦 圭一郎, 南角 吉彦, 李 晃伸, 徳田 恵一
音響学会公演論文集 87 - 88 2006.10
Language：Japanese Publishing type：Research paper (other academic)
-
An EM-type training algorithm for trajectory-HMM using Gibbs sampling
Heiga ZEN, Yoshihiko NANKAKU, Keiichi TOKUDA, Tadashi KITAMURA
Meeting of the Acoustical Society of Japan 89 - 90 2005.10
Language：Japanese Publishing type：Research paper (other academic)
-
Applying Sparse KPCA for Feature Extraction in Speech Recognition Reviewed
Amaro LIMA, Heiga ZEN, Yoshihiko NANKAKU, Keiichi TOKUDA, Tadashi KITAMURA, Fernando Gil Resende
IEICE Transactions on Information Systems E88-D ( 3 ) 401 - 409 2005.03
Language：English Publishing type：Research paper (scientific journal)
-
Continuous Speech Recognition Based on General Factor Dependent Acoustic Models Reviewed
Hiroyuki SUZUKI, Heiga ZEN, Yoshihiko NANKAKU, Chiyomi MIYAJIMA, Keiichi TOKUDA, Tadashi KITAMURA
IEICE Transactions on Information Systems E88-D ( 3 ) 410 - 417 2005.03
Language：English Publishing type：Research paper (scientific journal)
-
Parameter Sharing in Mixture of Factor Analyzers for Speaker Identification Reviewed
Hiroyoshi YAMAMOTO, Yoshihoko NANKAKU, Chiyomi MIYAJIMA, Keiichi TOKUDA, Tadashi KITAMURA
IEICE Transactions on Information Systems, Vol., no.3, pp., Mar, 2005 E88-D ( 3 ) 418 - 424 2005.03
Language：English Publishing type：Research paper (scientific journal)
-
Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition Reviewed
Yohei ITAYA, Heiga ZEN, Yoshihiko NANKAKU, Chiyomi MIYAJIMA, Keiichi TOKUDA, Tadashi KITAMURA
IEICE Transactions on Information Systems E88-D ( 3 ) 425 - 431 2005.03
Language：English Publishing type：Research paper (scientific journal)
-
On the use of kernel PCA for feature extraction in speech recognition Reviewed
Amaro LIMA, Heiga ZEN, Yoshihiko NANKAKU, Chiyomi MIYAJIMA, Keiichi TOKUDA, Tadashi KITAMURA
IEICE Transactions E88-D ( 3 ) 2802 - 2811 2004.12
Language：English Publishing type：Research paper (scientific journal)
-
A Baysian Approach to HMM-Based Speech Synthesis
Yoshihiko NANKAKU, Heiga ZEN, Keiichi TOKUDA, Tadashi KITAMURA, Takashi MASUKO
Technical Report of IEICE 103 ( 264 ) 19 - 24 2003.08
Language：Japanese Publishing type：Research paper (other academic)
-
Normalized Training for HMM-Based Visual Speech Recognition Reviewed
Yoshihiko NANKAKU, Keiichi TOKUDA, Tadashi KITAMURA, Takao KOBAYASHI
IEICE Transactions J86-D-II ( 2 ) 163 - 172 2003.02
Language：Japanese Publishing type：Research paper (scientific journal)
-
A Training Algorithm Based on Variational Approximation for Separable 2D-HMM
Technical Report of IEICE 102 ( 652 ) 1 - 6 2003.02
Language：Japanese Publishing type：Research paper (other academic)
PREV - NEXT 