Get started
Author

Yosuke Higuchi

Recent Developments on Espnet Toolkit Boosted By Conformer
2021 · Pengcheng Guo, Florian Boyer, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 205
Mask CTC: Non-Autoregressive End-to-End ASR with CTC and Mask Predict
2020 · Yosuke Higuchi, Shinji Watanabe, et al. · Interspeech (USB) · 123
PDF
Improved Mask-CTC for Non-Autoregressive End-to-End ASR
2021 · Yosuke Higuchi, Hirofumi Inaguma, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 51
A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
2021 · Yosuke Higuchi, Nanxin Chen, et al. · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · 42
PDF
The 2020 ESPnet Update: New Features, Broadened Applications, Performance Improvements, and Future Plans
2021 · Shinji Watanabe, Florian Boyer, et al. · IEEE Data Science Workshop (DSW) · 37
PDF
Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition
2021 · Yosuke Higuchi, Niko Moritz, et al. · Interspeech (USB) · 34
Recent Developments on ESPnet Toolkit Boosted by Conformer
2020 · Guo, Pengcheng, Boyer, Florian, et al. · arXiv (Cornell University) · 33
PDF
Improving Non-Autoregressive End-to-End Speech Recognition with Pre-Trained Acoustic and Language Models
2022 · Keqi Deng, Zehui Yang, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 25
CTC Alignments Improve Autoregressive Translation
2023 · Brian Yan, Siddharth Dalmia, et al. · Conference of the European Chapter of the Association for Computational Linguistics · 24
PDF
Momentum Pseudo-Labeling: Semi-Supervised ASR With Continuously Improving Pseudo-Labels
2022 · Yosuke Higuchi, Niko Moritz, et al. · IEEE Journal of Selected Topics in Signal Processing · 24
PDF
ORTHROS: non-autoregressive end-to-end speech translation With dual-decoder
2021 · Hirofumi Inaguma, Yosuke Higuchi, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 22
BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Model
2022 · Yosuke Higuchi, Brian Yan, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 20
PDF
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
2022 · Yosuke Higuchi, Keita Karube, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 19
A Study on the Integration of Pre-Trained SSL, ASR, LM and SLU Models for Spoken Language Understanding
2023 · Yifan Peng, Siddhant Arora, et al. · IEEE Spoken Language Technology Workshop (SLT) · 16
PDF
BECTRA: Transducer-Based End-To-End ASR with Bert-Enhanced Encoder
2023 · Yosuke Higuchi, Tetsuji Ogawa, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 12
PDF
ESPnet-ONNX: Bridging a Gap Between Research and Production
2022 · Masao Someki, Yosuke Higuchi, et al. · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · 8
PDF
Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy
2022 · Yosuke Higuchi, Niko Moritz, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 7
Speaker Adversarial Training of DPGMM-Based Feature Extractor for Zero-Resource Languages
2019 · Yosuke Higuchi, Naohiro Tawara, et al. · Interspeech (USB) · 6
Mask-Conformer: Augmenting Conformer with Mask-Predict Decoder
2023 · Yosuke Higuchi, Andrew Rosenberg, et al. · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · 5
Noise-robust Attention Learning for End-to-End Speech Recognition
2020 · Yosuke Higuchi, Naohiro Tawara, et al. · European Signal Processing Conference (EUSIPCO) · 5
Improved Mask-CTC for Non-Autoregressive End-to-End ASR
2020 · Higuchi, Yosuke, Inaguma, Hirofumi, et al. · arXiv (Cornell University) · 5
PDF
Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring
2021 · Inaguma, Hirofumi, Higuchi, Yosuke, et al. · arXiv (Cornell University) · 4
PDF
Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition
2021 · Higuchi, Yosuke, Moritz, Niko, et al. · arXiv (Cornell University) · 4
PDF
An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASR
2021 · Zhao, Huaibo, Higuchi, Yosuke, et al. · arXiv (Cornell University) · 3
PDF
Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units
2021 · Higuchi, Yosuke, Karube, Keita, et al. · arXiv (Cornell University) · 3
PDF
Works count: 51
Citation count: 748
H-index: 14
I10-index: 15
Year
Topic
Type