Yosuke Kashiwagi

发表

Streaming Transformer ASR with Blockwise Synchronous Inference pdf

Shinji Watanabe, Emiru Tsunoo, Yosuke Kashiwagi, 2020, ArXiv.

Automatic Assessment and Error Detection of Shadowing Speech: Case of English Spoken by Japanese Learners

Nobuaki Minematsu, Yutaka Yamauchi, Junwei Yue, 2016, INTERSPEECH.

Noise-robust and stress-free visualization of pronunciation diversity of World Englishes using a learner's self-centered viewpoint

Keikichi Hirose, Nobuaki Minematsu, Yuichi Sato, 2015, 2015 International Conference Oriental COCOSDA held jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE).

Discriminative Piecewise Linear Transformation Based on Deep Neural Networks for Noise Robust Automatic Speech Recognition

Keikichi Hirose, Nobuaki Minematsu, Yosuke Kashiwagi, 2016 .

End-to-end Adaptation with Backpropagation through WFST for On-device Speech Recognition System

Satoshi Asakawa, Emiru Tsunoo, Yosuke Kashiwagi, 2019, INTERSPEECH.

Semi-supervised noise dictionary adaptation for exemplar-based noise robust speech recognition

Keikichi Hirose, Nobuaki Minematsu, Yosuke Kashiwagi, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Discriminative piecewise linear transformation based on deep learning for noise robust automatic speech recognition

Keikichi Hirose, Nobuaki Minematsu, Yosuke Kashiwagi, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Audio-visual feature integration based on piecewise linear transformation for noise robust automatic speech recognition

Keikichi Hirose, Nobuaki Minematsu, Yosuke Kashiwagi, 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

Streaming Transformer Asr With Blockwise Synchronous Beam Search

Shinji Watanabe, Emiru Tsunoo, Yosuke Kashiwagi, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

Transformer ASR with Contextual Block Processing

Shinji Watanabe, Emiru Tsunoo, Yosuke Kashiwagi, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Divergence estimation based on deep neural networks and its use for language identification

Nobuaki Minematsu, Yosuke Kashiwagi, Daisuke Saito, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Towards Online End-to-end Transformer Automatic Speech Recognition pdf

Shinji Watanabe, Emiru Tsunoo, Yosuke Kashiwagi, 2019, ArXiv.

Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models pdf

Yosuke Kashiwagi, Ryosuke Sawata, Shusuke Takahashi, 2021, ArXiv.

Gaussian Kernelized Self-Attention for Long Sequence Data and its Application to CTC-Based Speech Recognition

Shinji Watanabe, Emiru Tsunoo, Yosuke Kashiwagi, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Data Augmentation Methods for End-to-end Speech Recognition on Distant-Talk Scenarios pdf

Shinji Watanabe, Emiru Tsunoo, Yosuke Kashiwagi, 2021, Interspeech.

Run-and-Back Stitch Search: Novel Block Synchronous Decoding For Streaming Encoder-Decoder ASR

Emiru Tsunoo, Yosuke Kashiwagi, Chaitanya Narisetty, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Streaming Transformer ASR with Blockwise Synchronous Inference pdf

Shinji Watanabe, Emiru Tsunoo, Yosuke Kashiwagi, 2020, ArXiv.