Presentations -
-
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
Event date： 2019.09
Language：Japanese Presentation type：Oral presentation (general)
-
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
Event date： 2019.09
Language：Japanese Presentation type：Oral presentation (general)
-
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
Event date： 2019.09
Language：Japanese Presentation type：Oral presentation (general)
-
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
音声言語情報処理研究会
Event date： 2019.06
Language：Japanese Presentation type：Oral presentation (general)
-
Singing voice synthesis based on generative adversarial networks International conference
Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019)
Event date： 2019.05
Language：English Presentation type：Poster presentation
-
Speaker-dependent WaveNet-based delay-free ADPCM speech coding International conference
Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019)
Event date： 2019.05
Language：English Presentation type：Poster presentation
-
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
Event date： 2019.03
Language：Japanese Presentation type：Oral presentation (general)
-
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
Event date： 2019.03
Language：Japanese Presentation type：Oral presentation (general)
-
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
Event date： 2019.03
Language：Japanese Presentation type：Oral presentation (general)
-
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
Event date： 2019.03
Language：Japanese Presentation type：Oral presentation (general)
-
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
Event date： 2019.03
Language：Japanese Presentation type：Oral presentation (general)
-
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
Event date： 2019.03
Language：Japanese Presentation type：Oral presentation (general)
-
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
Event date： 2019.03
Language：Japanese Presentation type：Oral presentation (general)
-
WaveNet-based zero-delay lossless speech coding International conference
Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
2018 IEEE Workshop on Spoken Language Technology (SLT 2018)
Event date： 2018.12
Language：English Presentation type：Oral presentation (general)
-
Image recognition based on convolutional neural networks using features generated from separable lattice hidden Markov models International conference
Takayuki Kasugai, Yoshinari Tsuzuki, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018 (APSIPA ASC 2018)
Event date： 2018.11
Language：English Presentation type：Oral presentation (general)
-
Speaker adaptation for speech synthesis based on deep neural networks using hidden semi-Markov model structures International conference
Kento Nakao, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018 (APSIPA ASC 2018)
Event date： 2018.11
Language：English Presentation type：Oral presentation (general)
-
Speech synthesis using WaveNet vocoder based on periodic/aperiodic decomposition International conference
Takato Fujimoto, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018 (APSIPA ASC 2018)
Event date： 2018.11
Language：English Presentation type：Oral presentation (general)
-
Discriminative feature extraction based on sequential variational autoencoder for speaker recognition International conference
Takenori Yoshimura, Natsumi Koike, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018 (APSIPA ASC 2018)
Event date： 2018.11
Language：English Presentation type：Oral presentation (general)
-
Recent development of the DNN-based singing voice synthesis system - Sinsy International conference
Yukiya Hono, Shumma Murata, Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018 (APSIPA ASC 2018)
Event date： 2018.11
Language：English Presentation type：Oral presentation (general)
-
Singing voice conversion using posted waveform data on music social media International conference
Koki Senda, Yukiya Hono, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2018 (APSIPA ASC 2018)
Event date： 2018.11
Language：English Presentation type：Poster presentation
