Follow
Yosuke Higuchi
Yosuke Higuchi
Verified email at pcl.cs.waseda.ac.jp - Homepage
Title
Cited by
Cited by
Year
Recent developments on espnet toolkit boosted by conformer
P Guo, F Boyer, X Chang, T Hayashi, Y Higuchi, H Inaguma, N Kamo, C Li, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
2762021
Mask CTC: Non-autoregressive end-to-end ASR with CTC and mask predict
Y Higuchi, S Watanabe, N Chen, T Ogawa, T Kobayashi
arXiv preprint arXiv:2005.08700, 2020
1292020
Improved Mask-CTC for non-autoregressive end-to-end ASR
Y Higuchi, H Inaguma, S Watanabe, T Ogawa, T Kobayashi
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
632021
The 2020 espnet update: new features, broadened applications, performance improvements, and future plans
S Watanabe, F Boyer, X Chang, P Guo, T Hayashi, Y Higuchi, T Hori, ...
2021 IEEE Data Science and Learning Workshop (DSLW), 1-6, 2021
532021
Momentum pseudo-labeling for semi-supervised speech recognition
Y Higuchi, N Moritz, JL Roux, T Hori
arXiv preprint arXiv:2106.08922, 2021
472021
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
462021
CTC alignments improve autoregressive translation
B Yan, S Dalmia, Y Higuchi, G Neubig, F Metze, AW Black, S Watanabe
arXiv preprint arXiv:2210.05200, 2022
282022
Improving non-autoregressive end-to-end speech recognition with pre-trained acoustic and language models
K Deng, Z Yang, S Watanabe, Y Higuchi, G Cheng, P Zhang
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
252022
BERT meets CTC: New formulation of end-to-end speech recognition with pre-trained masked language model
Y Higuchi, B Yan, S Arora, T Ogawa, T Kobayashi, S Watanabe
arXiv preprint arXiv:2210.16663, 2022
222022
Hierarchical conditional end-to-end asr with ctc and multi-granular subword units
Y Higuchi, K Karube, T Ogawa, T Kobayashi
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
222022
Orthros: Non-autoregressive end-to-end speech translation with dual-decoder
H Inaguma, Y Higuchi, K Duh, T Kawahara, S Watanabe
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
192021
A study on the integration of pre-trained ssl, asr, lm and slu models for spoken language understanding
Y Peng, S Arora, Y Higuchi, Y Ueda, S Kumar, K Ganesan, S Dalmia, ...
2022 IEEE Spoken Language Technology Workshop (SLT), 406-413, 2023
182023
Momentum pseudo-labeling: Semi-supervised asr with continuously improving pseudo-labels
Y Higuchi, N Moritz, J Le Roux, T Hori
IEEE Journal of Selected Topics in Signal Processing 16 (6), 1424-1438, 2022
172022
Advancing momentum pseudo-labeling with conformer and initialization strategy
Y Higuchi, N Moritz, J Le Roux, T Hori
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
122022
Bectra: Transducer-based end-to-end asr with bert-enhanced encoder
Y Higuchi, T Ogawa, T Kobayashi, S Watanabe
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
92023
Non-autoregressive end-to-end speech translation with parallel autoregressive rescoring
H Inaguma, Y Higuchi, K Duh, T Kawahara, S Watanabe
arXiv preprint arXiv:2109.04411, 2021
72021
Speaker embeddings incorporating acoustic conditions for diarization
Y Higuchi, M Suzuki, G Kurata
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
72020
Speaker Adversarial Training of DPGMM-Based Feature Extractor for Zero-Resource Languages.
Y Higuchi, N Tawara, T Kobayashi, T Ogawa
INTERSPEECH, 266-270, 2019
62019
Espnet-ONNX: Bridging a gap between research and production
M Someki, Y Higuchi, T Hayashi, S Watanabe
2022 Asia-Pacific Signal and Information Processing Association Annual …, 2022
42022
An investigation of enhancing CTC model for triggered attention-based streaming ASR
H Zhao, Y Higuchi, T Ogawa, T Kobayashi
2021 Asia-Pacific Signal and Information Processing Association Annual …, 2021
32021
The system can't perform the operation now. Try again later.
Articles 1–20