フォロー
Yuya Fujita
Yuya Fujita
Yahoo Japan Corporation
確認したメール アドレス: ieee.org
タイトル
引用先
引用先
Speech enhancement using end-to-end speech recognition objectives
AS Subramanian, X Wang, MK Baskar, S Watanabe, T Taniguchi, D Tran, ...
2019 IEEE Workshop on Applications of Signal Processing to Audio and …, 2019
602019
A comparative study on non-autoregressive modelings for speech-to-text generation
Y Higuchi, N Chen, Y Fujita, H Inaguma, T Komatsu, J Lee, J Nozaki, ...
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 47-54, 2021
422021
Insertion-based modeling for end-to-end automatic speech recognition
Y Fujita, S Watanabe, M Omachi, X Chan
arXiv preprint arXiv:2005.13211, 2020
372020
End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation
X Chang, T Maekaku, Y Fujita, S Watanabe
arXiv preprint arXiv:2204.00540, 2022
362022
Attention-based asr with lightweight and dynamic convolutions
Y Fujita, AS Subramanian, M Omachi, S Watanabe
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
202020
Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learning
X Chang, B Yan, Y Fujita, T Maekaku, S Watanabe
arXiv preprint arXiv:2305.18108, 2023
152023
Streaming End-to-End ASR Based on Blockwise Non-Autoregressive Models
T Wang, Y Fujita, X Chang, S Watanabe
arXiv preprint arXiv:2107.09428, 2021
142021
Speech representation learning combining conformer cpc with deep cluster for the zerospeech challenge 2021
T Maekaku, X Chang, Y Fujita, LW Chen, S Watanabe, A Rudnicky
arXiv preprint arXiv:2107.05899, 2021
132021
End-to-End ASR with Adaptive Span Self-Attention.
X Chang, AS Subramanian, P Guo, S Watanabe, Y Fujita, M Omachi
INTERSPEECH, 3595-3599, 2020
132020
Generalized weighted-prediction-error dereverberation with varying source priors for reverberant speech recognition
T Taniguchi, AS Subramanian, X Wang, D Tran, Y Fujita, S Watanabe
2019 IEEE Workshop on Applications of Signal Processing to Audio and …, 2019
92019
End-to-end ASR to jointly predict transcriptions and linguistic annotations
M Omachi, Y Fujita, S Watanabe, M Wiesner
Proceedings of the 2021 Conference of the North American Chapter of the …, 2021
82021
Speaker selective beamformer with keyword mask estimation
Y Kida, D Tran, M Omachi, T Taniguchi, Y Fujita
2018 IEEE Spoken Language Technology Workshop (SLT), 528-534, 2018
82018
Partial differential equation-based algorithm of sound source localization with finest granularity in both time and frequency
S Ando, N Ono, Y Fujita
2007 Fourth International Conference on Networked Sensing Systems, 229-234, 2007
82007
Robust DNN-Based VAD Augmented with Phone Entropy Based Rejection of Background Speech.
Y Fujita, K Iso
Interspeech, 3663-3667, 2016
72016
Attention Weight Smoothing Using Prior Distributions for Transformer-Based End-to-End ASR}}
T Maekaku, Y Fujita, Y Peng, S Watanabe
Proc. Interspeech 2022, 1071-1075, 2022
62022
Toward Streaming ASR with Non-Autoregressive Insertion-based Model
Y Fujita, T Wang, S Watanabe, M Omachi
arXiv preprint arXiv:2012.10128, 2020
62020
Partial‐differential‐equation‐based sound source localization: Finite Fourier integral approach and its application to multiple source localization
Y Fujita, N Ono, S Ando
The Journal of the Acoustical Society of America 120 (5), 3212-3212, 2006
62006
An Exploration of Hubert with Large Number of Cluster Units and Model Assessment Using Bayesian Information Criterion
T Maekaku, X Chang, Y Fujita, S Watanabe
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
52022
Non-Autoregressive End-To-End Automatic Speech Recognition Incorporating Downstream Natural Language Processing
M Omachi, Y Fujita, S Watanabe, T Wang
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
52022
Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation
M Omachi, B Yan, S Dalmia, Y Fujita, S Watanabe
arXiv preprint arXiv:2211.05967, 2022
22022
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–20