Yusuke Shinohara

发表

Adversarial Multitask Learning of Deep Neural Networks for Robust Speech Recognition

Yusuke Shinohara, 2016 .

Adversarial Multi-Task Learning of Deep Neural Networks for Robust Speech Recognition

Yusuke Shinohara, Yusuke Shinohara, 2016, INTERSPEECH.

Tying rotations of covariance matrices via riemannian subspace clustering

Yusuke Shinohara, Yusuke Shinohara, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Self-Distillation for Improving CTC-Transformer-Based ASR Systems

Marc Delcroix, Ryo Masumura, Tsubasa Ochiai, 2020, INTERSPEECH.

Minimum latency training of sequence transducers for streaming end-to-end speech recognition

Shinji Watanabe, Yusuke Shinohara, 2022, INTERSPEECH.

A Study of Transducer Based End-to-End ASR with ESPnet: Architecture, Auxiliary Loss and Decoding Strategies pdf

Shinji Watanabe, Yusuke Shinohara, Hirofumi Inaguma, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Simpleflat: A Simple Whole-Network Pre-Training Approach for RNN Transducer-Based End-to-End Speech Recognition

Yusuke Ijima, Hiroshi Sato, Tsubasa Ochiai, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Distilling Attention Weights for CTC-Based ASR Systems

Ryo Masumura, Hiroshi Sato, Takafumi Moriya, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Efficient Building Strategy with Knowledge Distillation for Small-Footprint Acoustic Models

Yusuke Shinohara, Manabu Okamoto, Yoshikazu Yamaguchi, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Sequence-Level Consistency Training for Semi-Supervised End-to-End Automatic Speech Recognition

Akihiko Takashima, Ryo Masumura, Takafumi Moriya, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Large Context End-to-end Automatic Speech Recognition via Extension of Hierarchical Recurrent Encoder-decoder Models

Takanobu Oba, Yusuke Shinohara, Tomohiro Tanaka, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Encoder Transfer for Attention-based Acoustic-to-word Speech Recognition

Tatsuya Kawahara, Shinsuke Sakai, Yusuke Shinohara, 2018, INTERSPEECH.

Multi-task Learning with Augmentation Strategy for Acoustic-to-word Attention-based Encoder-decoder Speech Recognition

Marc Delcroix, Yusuke Shinohara, Sei Ueno, 2018, INTERSPEECH.

Adversarial Training for Multi-task and Multi-lingual Joint Modeling of Utterance Intent Classification

Ryuichiro Higashinaka, Yusuke Shinohara, Ryo Masumura, 2018, EMNLP.

Neural Whispered Speech Detection with Imbalanced Learning

Hiroshi Sato, Yusuke Shinohara, Yoshikazu Yamaguchi, 2019, INTERSPEECH.

Bayesian feature enhancement using a mixture of unscented transformation for uncertainty decoding of noisy speech

Masami Akamine, Yusuke Shinohara, Yusuke Shinohara, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Revisiting Dynamic Adjustment of Language Model Scaling Factor for Automatic Speech Recognition

Ryo Masumura, Yoshikazu Yamaguchi, Takafumi Moriya, 2019, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Facial expression recognition using Fisher weight maps

Nobuyuki Otsu, Yusuke Shinohara, N. Otsu, 2004, Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings..