People
Yusuke Fujita Software Engineer
Received his B.S. and M.S. degrees in computer science from Waseda University, Tokyo, Japan, in 2003 and 2005, respectively. He was a Senior Researcher at Hitachi, Ltd. in Tokyo, Japan (2005-2021), and was a Visiting Scholar at Johns Hopkins University, MD, USA (2018-2020). He received his Doctor of Engineering degree from Waseda University in 2024. His research interests include speech recognition, speaker diarization, and music signal processing. He has been working on end-to-end speaker diarization and distant speech recognition, contributing to conferences like Interspeech and ICASSP.
Publications
-
- OTHERS (INTERNATIONAL)
- Song Data Cleansing for End-to-End Neural Singer Diarization Using Neural Analysis and Synthesis Framework
- Hokuto Munakata, Ryo Terashima, Yusuke Fujita
- arXiv.org
- June 24, 2024
-
- CONFERENCE (INTERNATIONAL)
- Audio Difference Learning for Audio Captioning
- Tatsuya Komatsu, Yusuke Fujita, Kazuya Takeda (Nagoya University), Tomoki Toda (Nagoya University)
- 2024 IEEE International Conference on Acoustics, Speech and Signal Processing
- April 14, 2024
-
- CONFERENCE (INTERNATIONAL)
- Keep Decoding Parallel With Effective Knowledge Distillation From Language Models To End-To-End Speech Recognisers
- Michael Hentschel (LINE WORKS Corporation), Yuta Nishikawa (Nara Institute of Science and Technology), Tatsuya Komatsu, Yusuke Fujita
- 2024 IEEE International Conference on Acoustics, Speech and Signal Processing
- April 14, 2024
-
- CONFERENCE (DOMESTIC)
- 日本語テキストと音楽の対照学習の実験的評価
- 蓮実 拓也, 小松 達也, 藤田 雄介, 二又 航介, 橘 健太郎
- 日本音響学会 2024年春季研究発表会
- March 07, 2024
-
- CONFERENCE (DOMESTIC)
- 拡散過程と敵対的学習の併用による普遍音声強調
- シャイブラー ロビン, 藤田 雄介, 橘 健太郎
- 日本音響学会 2024年春季研究発表会
- March 06, 2024
-
- JOURNAL (INTERNATIONAL)
- Self-conditioning via Intermediate Predictions for End-to-end Neural Speaker Diarization
- Yusuke Fujita, Tetsuji Ogawa (Waseda University), Tetsunori Kobayashi (Waseda University)
- IEEE Access
- December 07, 2023
-
- CONFERENCE (DOMESTIC)
- End-to-end 音声認識器の中間層への言語知識転移
- Michael Hentschel (WORKS MOBILE JAPAN), 西川 勇太 (奈良先端科学技術大学院大学), 小松 達也, 藤田 雄介
- 日本音響学会 2023年秋季研究発表会
- September 26, 2023
-
- CONFERENCE (DOMESTIC)
- Foley Sound Synthesis with a Class-Conditioned Latent Diffusion Model and FAD-Based Post-filtering
- シャイブラー ロビン, 蓮実 拓也, 藤田 雄介, 小松 達也, 山本 龍一, 橘 健太郎
- 日本音響学会 2023年秋季研究発表会
- September 26, 2023
-
- WORKSHOP (INTERNATIONAL)
- Foley Sound Synthesis with a Class-conditioned Latent Diffusion Model
- Robin Scheibler, Takuya Hasumi, Yusuke Fujita, Tatsuya Komatsu, Ryuichi Yamamoto, Kentaro Tachibana
- Detection and Classification of Acoustic Scenes and Events
- September 20, 2023
-
- CONFERENCE (INTERNATIONAL)
- Target Vocabulary Recognition Based on Multi-Task Learning with Decomposed Teacher Sequences
- Aoi Ito (Hosei University), Tatsuya Komatsu, Yusuke Fujita, Yusuke Kida
- The 24th Annual Conference of the International Speech Communication Association
- August 20, 2023
-
- CONFERENCE (INTERNATIONAL)
- Neural Diarization with Non-Autoregressive Intermediate Attractors
- Yusuke Fujita, Tatsuya Komatsu, Robin Scheibler, Yusuke Kida, Tetsuji Ogawa (Waseda University)
- 2023 IEEE International Conference on Acoustics, Speech and Signal Processing
- June 04, 2023
-
- CONFERENCE (DOMESTIC)
- 中間層予測を用いたEnd-to-end ダイアライゼーション
- 藤田 雄介, 小松 達也, Scheibler Robin, 木田 祐介, 小川 哲司 (早稲田大学)
- 日本音響学会 2023年春季研究発表会
- March 15, 2023
-
- OTHERS (DOMESTIC)
- 日本語音声認識における語彙集合分割とマルチタスク学習による 目的語彙抽出
- 伊藤 葵 (LINE/法政大学), 小松 達也, 藤田 雄介
- 電子情報通信学会/日本音響学会 音声研究会
- February 28, 2023
-
- CONFERENCE (INTERNATIONAL)
- Alternate Intermediate Conditioning with Syllable-level and Character-level Targets for Japanese ASR
- Yusuke Fujita, Tatsuya Komatsu, Yusuke Kida
- The 2022 IEEE Spoken Language Technology Workshop
- January 09, 2023
-
- CONFERENCE (INTERNATIONAL)
- Inter-Decoder: Using Attention-Decoder losses as Intermediate Regularization for CTC-based Speech Recognition
- Tatsuya Komatsu, Yusuke Fujita
- The 2022 IEEE Spoken Language Technology Workshop
- January 09, 2023
-
- CONFERENCE (INTERNATIONAL)
- On Sorting and Padding Multiple Targets for Sound Event Localization and Detection with Permutation Invariant and Location-based Training
- Robin Scheibler, Tatsuya Komatsu, Yusuke Fujita, Michael Hentschel
- Asia-Pacific Signal and Information Processing Association Annual Summit and Conference 2022
- November 07, 2022
-
- WORKSHOP (INTERNATIONAL)
- Sound Event Localization and Detection with pre-trained Audio Spectrogram Transformer and Multichannel Separation Network
- Robin Scheibler, Tatsuya Komatsu, Yusuke Fujita, Michael Hentschel
- Detection and Classification of Acoustic Scenes and Events
- November 03, 2022
-
- CONFERENCE (INTERNATIONAL)
- Better Intermediates Improve CTC Inference
- Tatsuya Komatsu, Yusuke Fujita, Jaesong Lee (NAVER), Lukas Lee (NAVER), Shinji Watanabe (Carnegie Mellon University), Yusuke Kida
- The 23rd Annual Conference of the International Speech Communication Association
- September 18, 2022
-
- CONFERENCE (INTERNATIONAL)
- 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
- September 18, 2022
-
- CONFERENCE (DOMESTIC)
- 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
- September 14, 2022