Publications

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

カンファレンス (国際)
NON-AUTOREGRESSIVE END-TO-END AUTOMATIC SPEECH RECOGNITION INCORPORATING DOWNSTREAM NATURAL LANGUAGE PROCESSING: Motoi Omachi, Yuya Fujita, Shinji Watanabe (Carnegie Mellon University), Tianzi Wang (Johns Hopkins University); 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2022); 2022.4.27

その他 (国際)
End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation: Xuankai Chang (Carnegie Mellon University), Takashi Maekaku, Yuya Fujita, Shinji Watanabe (Carnegie Mellon University); arXiv.org (arXiv); 2022.4.1

カンファレンス (国際)
Robust Noise Canceller Algorithm with SNR-Based Stepsize Control and Gain Adjustment: Akihiko Sugiyama; International Conference on Consumer Electronics 2022 (ICCE2022); 2022.1.7

ワークショップ (国際)
AN EXPLORATION OF SELF-SUPERVISED PRETRAINED REPRESENTATIONS FOR END-TO-END SPEECH RECOGNITION: Xuankai Chang (Carnegie Mellon University), Takashi Maekaku, Pengcheng Guo (Northwestern Polytechnical University), Jing Shi (Institute of Automation, Chinese Academy of Sciences), Yen, Aswin Shanmugam Subramanian (Johns Hopkins University), Tianzi Wang (Johns Hopkins University), Shu, Yu Tsao (Academia Sinica), Hung, Shinji Watanabe (Carnegie Mellon University); IEEE Automatic Speech Recognition and Understanding Workshop 2021 (ASRU 2021); 2021.12.15

ワークショップ (国際)
A COMPARATIVE STUDY ON NON-AUTOREGRESSIVE MODELINGS FOR SPEECH-TO-TEXT GENERATION: Yosuke Higuchi (Waseda University), Nanxin Chen (Johns Hopkins University), Yuya Fujita, Hirofumi Inaguma (Kyoto University), Tatsuya Komatsu (LINE Corporation), Jaesong Lee (Naver Corporation), Jumon Nozaki (Kyoto University, LINE Corporation), Tianzi Wang (Johns Hopkins University), Shinji Watanabe (Carnegie Mellon University); The 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2021); 2021.12.14

ワークショップ (国際)
A Study of Transducer Based End-to-End ASR with ESPnet: Architecture, Auxiliary Loss and Decoding Strategies: Florian Boyer (Airudit, University of Bordeaux), Yusuke Shinohara, Takaaki Ishii, Hirofumi Inaguma (Kyoto University), Shinji Watanabe (Carnegie Mellon University); The 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2021); 2021.12.13

その他 (国際)
A COMPARATIVE STUDY ON NON-AUTOREGRESSIVE MODELINGS FOR SPEECH-TO-TEXT GENERATION: Yosuke Higuchi (Waseda University), Nanxin Chen (Johns Hopkins University), Yuya Fujita, Hirofumi Inaguma (Kyoto University), Tatsuya Komatsu (LINE Corporation), Jaesong Lee (Naver Corporation), Jumon Nozaki (Kyoto University, LINE Corporation), Tianzi Wang (Johns Hopkins University), Shinji Watanabe (Carnegie Mellon University); arXiv; 2021.10.11

カンファレンス (国内)
Conformer CPCとDeep Cluster を用いたゼロリソース言語のための表現学習: 前角高史, Xuankai Chang (カーネギーメロン大学), 藤田悠哉, Li-Wei Chen (カーネギーメロン大学), 渡部晋治(カーネギーメロン大学), Alexander Rudnicky (カーネギーメロン大学); 日本音響学会2021年秋季研究発表会; 2021.9.8

カンファレンス (国内)
音声意味理解への応用を指向した非自己回帰型End-to-end音声認識: 大町基, 藤田悠哉, 渡部晋治 (Carnegie Mellon University), Tianzi Wang (Johns Hopkins University); 日本音響学会　2021年秋季研究発表会 (音響学会); 2021.9.7

カンファレンス (国際)
Streaming End-to-End ASR based on Blockwise Non-Autoregressive Models: Tianzi Wang (Johns Hopkins University), Yuya Fujita, Xuankai Chang (Carnegie Mellon Univ.), Shinji Watanabe (Carnegie Mellon University); INTERSPEECH 2021; 2021.9.2

カンファレンス (国際)
Toward Streaming ASR with Non-Autoregressive Insertion-based Model: Yuya Fujita, Tianzi Wang (Johns Hopkins University), Shinji Watanabe (Carnegie Mellon University), Motoi Omach; INTERSPEECH 2021; 2021.9.2

カンファレンス (国際)
Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021: Takashi Maekaku, Xuankai Chang (Carnegie Mellon University), Yuya Fujita, Li, Shinji Watanabe (Carnegie Mellon University), Alexander Rudnicky (Carnegie Mellon University); INTERSPEECH 2021; 2021.8.30

その他 (国際)
Streaming End-to-End ASR based on Blockwise Non-Autoregressive Models: Tianzi Wang (Johns Hopkins Univ.), Yuya Fujita, Xuankai Chang (Carnegie Mellon Univ.), Shinji Watanabe (Carnegie Mellon Univ.); arXiv.org; 2021.7.20

その他 (国際)
Toward Streaming ASR with Non-Autoregressive Insertion-based Model: Yuya Fujita, Tianzi Wang (Johns Hopkins Univ.), Shinji Watanabe (Carnegie Mellon Univ.), Motoi Omachi; arXiv.org; 2021.7.16

カンファレンス (国際)
End-to-end ASR to jointly predict transcriptions and linguistic annotations: Motoi Omachi, Yuya Fujita, Shinji Watanabe (Johns Hopkins University), Matthew Wiesner (Johns Hopkins University); The 2021　North American Chapter of the Association for Computational Linguistics : Human Language Technologies (NAACL-HLT2021); 2021.6.6

カンファレンス (国内)
挿入操作に基づく End-to-End モデルによる音声認識と音声区間検出: 藤田悠哉, 渡部晋治 (Johns Hopkins Univ.), 大町基; 日本音響学会2021年春季研究発表会; 2021.3.10

その他 (国際)
End-to-End ASR and Audio Segmentation with Non-autoregressive Insertion-based model: Yuya Fujita, Shinji Watanabe (Johns Hopkins Univ.), Motoi Omachi; arXiv.org; 2020.12.18

論文誌 (国際)
Innovation, Standardization, and Business Success in Media Signal Processing: Akihiko Sugiyama and Masahiro Serizawa (NEC Corporation); Institute of Electrical and Electronics Engineers, Consumer Electronics Magazine (MCE); 2020.11.3

カンファレンス (国際)
End-to-End ASR with Adaptive Span Self-Attention: Xuankai Chang (Johns Hopkins University), Aswin Shanmugam Subramanian (Johns Hopkins University), Pengcheng Guo (Northwestern Polytechnical University, Johns Hopkins University), Shinji Watanabe (Johns Hopkins University), Yuya Fujita, Motoi Omachi; INTERSPEECH 2020; 2020.10.25