Presentations -
-
魅力ある音声インタラクションシステムを構築するためのオープンソースツールキットMMDAgent
李晃伸, 大浦圭一郎, 徳田恵一
音声言語シンポジウム
Event date： 2011.12
Language：Japanese Presentation type：Oral presentation (general)
Venue：東京
-
Speech synthesis as a statistical machine learning problem International conference
Keiichi Tokuda
2011 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2011)
Event date： 2011.12
Language：English Presentation type：Oral presentation (invited, special)
Venue：Hawaii, USA
-
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
PRMU 電子情報通信学会
Event date： 2011.11
Language：Japanese Presentation type：Oral presentation (general)
Venue：長崎大学 文教キャンパス
-
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
PRMU 電子情報通信学会
Event date： 2011.11
Language：Japanese Presentation type：Oral presentation (general)
Venue：長崎大学 文教キャンパス
-
Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2011 International conference
Kei Hashimoto, Shinji Takaki, Keiichiro Oura, Keiichi Tokuda
Blizzard Challenge 2011
Event date： 2011.09
Language：English Presentation type：Oral presentation (general)
Venue： Turin, Italy
-
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
Event date： 2011.09
Language：Japanese Presentation type：Oral presentation (general)
Venue：島根
-
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
Event date： 2011.09
Language：Japanese Presentation type：Oral presentation (general)
Venue：島根
-
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
Event date： 2011.09
Language：Japanese Presentation type：Oral presentation (general)
Venue：島根
-
Multi-Speaker Modeling with Shared Prior Distributions and Model Structures for Bayesian Speech Synthesis International conference
Kei Hashimoto, Yoshihiko Nankaku, Keiichi Tokuda
Interspeech 2011
Event date： 2011.08
Language：English Presentation type：Oral presentation (general)
Venue： Florence, Italy
-
Estimation of Perceptual Spaces for Speaker Identities Based on the Cross-Lingual Discrimination Task International conference
Minoru Tsuzaki, Keiichi Tokuda, Hisashi Kawai, Jinfu Ni
Interspeech 2011
Event date： 2011.08
Language：English Presentation type：Oral presentation (general)
Venue： Florence, Italy
-
A Bayesian Approach to Voice Conversion Based on GMMs Using Multiple Model Structures International conference
Lei Li, Yoshihiko Nankaku, Keiichi Tokuda
Interspeech 2011
Event date： 2011.08
Language：English Presentation type：Oral presentation (general)
Venue： Florence, Italy
-
GMM-based missing-feature reconstruction on multi-frame windows International conference
Ulpu Remes, Yoshihiko Nankaku, Keiichi Tokuda
Interspeech 2011
Event date： 2011.08
Language：English Presentation type：Poster presentation
Venue： Florence, Italy
-
Estimation of Window Coefficients for Dynamic Feature Extraction for HMM-based Speech Synthesis International conference
Ling-Hui Chen, Yoshihiko Nankaku, Heiga Zen, Keiichi Tokuda, Zhen-Hua Ling, Li-Rong Dai
Interspeech 2011
Event date： 2011.08
Language：English Presentation type：Poster presentation
Venue： Florence, Italy
-
Large-scale Subjective Evaluation of Speech Rate Control Methods for HMM-based Speech Synthesizers International conference
Tsuneo Kato, Makoto Yamada, Nobuyuki Nishizawa, Keiichiro Oura, Keiichi Tokuda
Interspeech 2011
Event date： 2011.08
Language：English Presentation type：Poster presentation
Venue： Florence, Italy
-
Evaluation of Tree-trellis based Decoding in Over-million LVCSR International conference
Naoaki Ito, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda
Interspeech 2011
Event date： 2011.08
Language：English Presentation type：Poster presentation
Venue： Florence, Italy
-
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
音声研究会
Event date： 2011.06
Language：Japanese Presentation type：Oral presentation (general)
Venue：名古屋
-
Global variance modeling on frequency domain delta LSP for HMM-based speech synthesis International conference
Shifeng Pan, Yoshihiko Nankaku, Keiichi Tokuda, Jianhua Tao
2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011) IEEE
Event date： 2011.05
Language：English Presentation type：Poster presentation
Venue：チェコ共和国プラハ市
-
An optimization algorithm of mean and variance parameter tying structures for HMM-based speech synthesis International conference
Shinji Takaki, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda
2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011) IEEE
Event date： 2011.05
Language：English Presentation type：Poster presentation
Venue：チェコ共和国プラハ市
-
An analysis of machine translation and speech synthesis in speech-to-speech translation system International conference
Kei Hashimoto, Junichi Yamagishi, William Byrne, Simon King, Keiichi Tokuda
2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011) IEEE
Event date： 2011.05
Language：English Presentation type：Poster presentation
Venue：チェコ共和国プラハ市
-
HMM音声認識における平均・分散パラメータの共有構造に関する検討
澤田 俊彦，高木 信二，南角 吉彦，李 晃伸，徳田 恵一
日本音響学会 2011年 春季研究発表会
Event date： 2011.03
Language：Japanese Presentation type：Oral presentation (general)
