Publications

カンファレンス (国際)
ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding: Yen-Ju Lu (Academia Sinica), Xuankai Chang (CMU), Chenda Li (SJTU), Wangyou Zhang (SJTU), Samuele Cornell (Universit`a Politecnica delle Marche), Zhaoheng Ni (Meta AI), Yoshiki Masuyama (CMU/TMU), Brian Yan (CMU), Robin Scheibler, Zhong-Qiu Wang (CMU), Yu Tsao (Academica Sinica), Yanmin Qian (SJTU), Shinji Watanabe (CMU); The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022); 2022.9.18

カンファレンス (国際)
Independence-based Joint Dereverberation and Separation with Neural Source Model: Kohei Saijo (Waseda University), Robin Scheilbler; The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022); 2022.9.18

カンファレンス (国際)
InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR: Yu Nakagome, Tatsuya Komatsu, Yusuke Fujita, Shuta Ichimura, Yusuke Kida; The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022); 2022.9.18

カンファレンス (国際)
Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems: Hyun-Wook Yoon (NAVER), Ohsung Kwon (NAVER), Hoyeon Lee (NAVER), Ryuichi Yamamoto, Eunwoo Song (NAVER), Jae-Min Kim (NAVER), Min-Jae Hwang (NAVER); The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022); 2022.9.18

カンファレンス (国際)
Minimum Latency Training of Sequence Transducers for Streaming End-to-End Speech Recognition: Yusuke Shinohara, Shinji Watanabe (Carnegie Mellon University); The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022); 2022.9.18

カンファレンス (国際)
Spatial Loss for Unsupervised Multi-channel Source Separation: Kohei Saijo (Waseda University), Robin Scheilbler; The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022); 2022.9.18

カンファレンス (国際)
STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent: Yuki Saito (The University of Tokyo), Yuto Nishimura (The University of Tokyo), Shinnosuke Takamichi (The University of Tokyo), Kentaro Tachibana, Hiroshi Saruwatari (The University of Tokyo); The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022); 2022.9.18

カンファレンス (国際)
TTS-by-TTS 2: Data-selective Augmentation for Neural Speech Synthesis Using Ranking Support Vector Machine with Variational Autoencoder: Eunwoo Song (NAVER), Ryuichi Yamamoto, Ohsung Kwon (NAVER), Chan-Ho Song, Min-Jae Hwang (NAVER), Suhyeon Oh (NAVER), Hyun-Wook Yoon (NAVER), Jin-Seob Kim (NAVER), Jae-Min Kim (NAVER); The 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022); 2022.9.18

カンファレンス (国内)
CTC ベース音声認識モデルにおける中間層ロスと条件付けが与える影響の考察: 市村収太, 中込優, 藤田雄介, 小松達也, 木田祐介; 日本音響学会 2022年秋季研究発表会 (ASJ 2022 autumn); 2022.9.14

カンファレンス (国内)
End-to-end Automatic Speech Recognition with Independent Vector Analysis Frontend: シャイブラーロビン, Zhang Wangyou (Shanghai Jiao Tong University), Chang Xuankai (Shanghai Jiao Tong University), 渡部晋治 (Carnegie Mellon University), Qian Yanmin (Shanghai Jiao Tong University); 日本音響学会 2022年秋季研究発表会 (ASJ 2022 autumn); 2022.9.14

カンファレンス (国内)
中間層予測にビームサーチを用いた新しい CTC 推論: 小松達也, 藤田雄介, Lee Jaesong (NAVER), Lee Lukas (NAVER), 渡部晋治 (Carnegie Mellon University), 木田祐介; 日本音響学会 2022年秋季研究発表会 (ASJ 2022 autumn); 2022.9.14

カンファレンス (国内)
中間層予測に対するノイズ付与による CTC 音声認識の頑健性向上: 中込優, 小松達也, 藤田雄介, 市村収太, 木田祐介; 日本音響学会 2022年秋季研究発表会 (ASJ 2022 autumn); 2022.9.14

カンファレンス (国内)
中間層予測に音節と表記を用いる日本語音声認識: 藤田雄介, 小松達也, 木田祐介; 日本音響学会 2022年秋季研究発表会 (ASJ 2022 autumn); 2022.9.14

カンファレンス (国内)
微分可能な信号処理に基づく音声合成器を用いた DNN 音声パラメータ推定の検討: 松永裕太 (LINE/東京大学), 寺島涼, 橘健太郎; 日本音響学会 2022年秋季研究発表会 (ASJ 2022 autumn); 2022.9.14

カンファレンス (国内)
音響シーン認識のためのサブアレイ間相関特徴量の検討: 河村隆生 (東京都立大学), 木下裕磨 (東京都立大学/東海大学), 小野順貴 (東京都立大学), シャイブラーロビン; 日本音響学会 2022年秋季研究発表会 (ASJ 2022 autumn); 2022.9.14

ワークショップ (国際)
User Preference between Residual Noise and Speech Distortion in Speech Enhancement: Akihiko Sugiyama, Osamu Shimada (NEC Corporation), Toshiyuki Nomura (NEC Corporation); International Workshop on Acoustic Signal Enhancement (IWAENC); 2022.9.5

カンファレンス (国際)
Non-Autoregressive ASR with Self-Conditioned Folded Encoders: Tatsuya Komatsu; 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022); 2022.5.22

カンファレンス (国際)
SDR -- Medium Rare with Fast Computations: Robin Scheilbler; 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022); 2022.5.22

カンファレンス (国際)
Self-Supervised Learning Method Using Multiple Sampling Strategies for General-Purpose Audio Representation: Ibuki Kuroyanagi (Nagoya University), Tatsuya Komatsu; 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022); 2022.5.22

カンファレンス (国際)
An Exploration of Hubert with Large Number of Cluster Units and Model Assessment Using Bayesian Information Criterion: Takashi Maekaku, Xuankai Chang (Carnegie Mellon University), Yuya Fujita, Shinji Watanabe (Carnegie Mellon University); The International Conference on Acoustics, Speech, & Signal Processing 2022 (ICASSP 2022); 2022.5.10