Yuya Fujita - LY Corporation R&D

CONFERENCE (DOMESTIC)
トピックモデルを用いた教師なし学習によるHuBERTの意味表現向上: 前角高史, Jiatong Shi (カーネギーメロン大学), Xuankai Chang (カーネギーメロン大学), 藤田悠哉, 渡部晋治 (カーネギーメロン大学); 日本音響学会 2024年秋季研究発表会; September 04, 2024

CONFERENCE (DOMESTIC)
離散トークン音声認識におけるドメイン適応の検討: 石井敬章, 小松達也, 藤田雄介, 藤田悠哉; 日本音響学会 2024年秋季研究発表会; September 04, 2024

JOURNAL (INTERNATIONAL)
MC-Whisper: Extending Speech Foundation Models to Multichannel Distant Speech Recognition: Xuankai Chang (Carnegie Mellon University), Pengcheng Guo (Northwestern Polytechnical University), Yuya Fujita, Takashi Maekaku, Shinji Watanabe (Carnegie Mellon University); IEEE Signal Processing Letters; August 26, 2024

CONFERENCE (INTERNATIONAL)
Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing: Brian Yan (Carnegie Mellon University), Xuankai Chang (Carnegie Mellon University), Antonios Anastasopoulos (George Mason University), Yuya Fujita, Shinji Watanabe (Carnegie Mellon University); 2024 IEEE International Conference on Acoustics, Speech and Signal Processing; April 14, 2024

OTHERS (INTERNATIONAL)
LV-CTC: Non-autoregressive ASR with CTC and latent variable models: Yuya Fujita, Shinji Watanabe (Carnegie Mellon Univ.), Xuankai Chang (Carnegie Mellon Univ.), Takashi Maekaku; arXiv.org; March 28, 2024

CONFERENCE (INTERNATIONAL)
Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study: Xuankai Chang (Carnegie Mellon University), Brian Yan (Carnegie Mellon University), Kwanghee Choi (Carnegie Mellon University), Jee-Weon Jung (Carnegie Mellon University), Yichen Lu (Carnegie Mellon University), Soumi Maiti (Carnegie Mellon University), Roshan Sharma (Carnegie Mellon University), Jiatong Shi (Carnegie Mellon University), Jinchuan Tian (Carnegie Mellon University), Shinji Watanabe (Carnegie Mellon University), Yuya Fujita, Takashi Maekaku, Pengcheng Guo (Northwestern Polytechnical University), Yao-Fei Cheng (University of Washington), Pavel Denisov (University of Stuttgart), Kohei Saijo (Waseda University), Hsiu-Hsuan Wang (National Taiwan University); 2024 IEEE International Conference on Acoustics, Speech and Signal Processing; March 20, 2024

CONFERENCE (INTERNATIONAL)
Hubertopic: Enhancing Semantic Representation of Hubert Through Self-Supervision Utilizing Topic Model: Takashi Maekaku, Jiatong Shi (Carnegie Mellon University), Xuankai Chang (Carnegie Mellon University), Yuya Fujita, Shinji Watanabe (Carnegie Mellon University); 2024 IEEE International Conference on Acoustics, Speech and Signal Processing; March 20, 2024

CONFERENCE (INTERNATIONAL)
LV-CTC: Non-autoregressive ASR with CTC and Latent Variable Models: Yuya Fujita, Shinji Watanabe (Carnegie Mellon Univ.), Xuankai Chang (Carnegie Mellon Univ.), Takashi Maekaku; The 2023 IEEE Workshop on Automatic Speech Recognition and Understanding; December 16, 2023

OTHERS (INTERNATIONAL)
HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model: Takashi Maekaku, Jiatong Shi (Carnegie Mellon University), Xuankai Chang (Carnegie Mellon University), Yuya Fujita, Shinji Watanabe (Carnegie Mellon University); arXiv; October 09, 2023

CONFERENCE (DOMESTIC)
潜在変数モデルを用いたCTCによる非自己回帰型音声認識: 藤田悠哉, 渡部晋治 (カーネギーメロン大学); 日本音響学会第150回(2023年秋季)研究発表会; September 26, 2023

CONFERENCE (INTERNATIONAL)
Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learning: Xuankai Chang (Carnegie Mellon University), Brian Yan (Carnegie Mellon University), Yuya Fujita, Takashi Maekaku, Shinji Watanabe (Carnegie Mellon University); The 24th Annual Conference of the International Speech Communication Association; August 20, 2023

CONFERENCE (INTERNATIONAL)
Fully Unsupervised Topic Clustering of Unlabelled Spoken Audio Using Self-Supervised Representation Learning and Topic Model: Takashi Maekaku, Yuya Fujita, Xuankai Chang (Carnegie Mellon University), Shinji Watanabe (Carnegie Mellon University); The International Conference on Acoustics, Speech, & Signal Processing 2023; June 07, 2023

OTHERS (INTERNATIONAL)
Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learning: Xuankai Chang (Carnegie Mellon University), Brian Yan (Carnegie Mellon University), Yuya Fujita, Takashi Maekaku, Shinji Watanabe (Carnegie Mellon University); arXiv; May 29, 2023

CONFERENCE (INTERNATIONAL)
Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation: Motoi Omachi, Brian Yan (Carnegie Mellon University), Siddharth Dalmia (Carnegie Mellon University), Yuya Fujita, Shinji Watanabe (Carnegie Mellon University); 2023 IEEE International Conference on Acoustics, Speech and Signal Processing; May 08, 2023

CONFERENCE (DOMESTIC)
訳語対の推定と順序入れ替え操作による説明可能なEnd-to-end音声翻訳: 大町基, Brian Yan (Carnegie Mellon University), Siddharth Dalmia (Carnegie Mellon University), 藤田悠哉, 渡部晋治 (Carnegie Mellon University); 日本音響学会2023年春季研究発表会; March 22, 2023

CONFERENCE (DOMESTIC)
Transformerを用いた音声認識モデルにおける事前分布を用いた注意重みの平滑化の検討: 前角高史, 藤田悠哉, Yifang Peng (Carnegie Mellon University), 渡部晋治 (Carnegie Mellon University); 日本音響学会2023年春季研究発表会; March 16, 2023

OTHERS (INTERNATIONAL)
Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation: Motoi Omachi, Brian Yan (Carnegie Mellon University), Siddharth Dalmia (Carnegie Mellon University), Yuya Fujita, Shinji Watanabe (Carnegie Mellon University); arXiv.org; November 14, 2022

CONFERENCE (INTERNATIONAL)
Attention Weight Smoothing Using Prior Distributions for Transformer-Based End-to-End ASR: Takashi Maekaku, Yuya Fujita, Yifan Peng (Carnegie Mellon University), Shinji Watanabe (Carnegie Mellon University); The 23rd Annual Conference of the International Speech Communication Association; September 19, 2022

CONFERENCE (INTERNATIONAL)
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); The 23rd Annual Conference of the International Speech Communication Association; September 19, 2022

CONFERENCE (INTERNATIONAL)
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; May 10, 2022

LY Corporation R&D