Follow
Hirofumi Inaguma
Hirofumi Inaguma
Research scientist, Fundamental AI Research (FAIR) at Meta
Verified email at meta.com - Homepage
Title
Cited by
Cited by
Year
A comparative study on transformer vs rnn in speech applications
S Karita, N Chen, T Hayashi, T Hori, H Inaguma, Z Jiang, M Someki, ...
2019 IEEE automatic speech recognition and understanding workshop (ASRU …, 2019
7402019
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
2542021
ESPnet-ST: All-in-one speech translation toolkit
H Inaguma, S Kiyono, K Duh, S Karita, NEY Soplin, T Hayashi, ...
arXiv preprint arXiv:2004.10234, 2020
1532020
Multilingual end-to-end speech translation
H Inaguma, K Duh, T Kawahara, S Watanabe
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019
812019
Acoustic-to-word attention-based model complemented with character-level CTC-based model
S Ueno, H Inaguma, M Mimura, T Kawahara
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
732018
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
592021
Leveraging sequence-to-sequence speech synthesis for enhancing acoustic-to-word speech recognition
M Mimura, S Ueno, H Inaguma, S Sakai, T Kawahara
2018 IEEE Spoken Language Technology Workshop (SLT), 477-484, 2018
592018
Minimum latency training strategies for streaming sequence-to-sequence ASR
H Inaguma, Y Gaur, L Lu, J Li, Y Gong
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
532020
Distilling the knowledge of BERT for sequence-to-sequence ASR
H Futami, H Inaguma, S Ueno, M Mimura, S Sakai, T Kawahara
arXiv preprint arXiv:2008.03822, 2020
522020
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
502021
Transfer learning of language-independent end-to-end ASR with language model fusion
H Inaguma, J Cho, MK Baskar, T Kawahara, S Watanabe
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
482019
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
442021
Source and target bidirectional knowledge distillation for end-to-end speech translation
H Inaguma, T Kawahara, S Watanabe
arXiv preprint arXiv:2104.06457, 2021
372021
Enhancing monotonic multihead attention for streaming asr
H Inaguma, M Mimura, T Kawahara
arXiv preprint arXiv:2005.09394, 2020
342020
SeamlessM4T-Massively Multilingual & Multimodal Machine Translation
L Barrault, YA Chung, MC Meglioli, D Dale, N Dong, PA Duquenne, ...
arXiv preprint arXiv:2308.11596, 2023
332023
A study of transducer based end-to-end ASR with ESPnet: Architecture, auxiliary loss and decoding strategies
F Boyer, Y Shinohara, T Ishii, H Inaguma, S Watanabe
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 16-23, 2021
272021
Findings of the IWSLT 2023 evaluation campaign
M Agarwal, S Agarwal, A Anastasopoulos, L Bentivogli, O Bojar, C Borg, ...
Association for Computational Linguistics, 2023
232023
Unity: Two-pass direct speech-to-speech translation with discrete units
H Inaguma, S Popuri, I Kulikov, PJ Chen, C Wang, YA Chung, Y Tang, ...
arXiv preprint arXiv:2212.08055, 2022
232022
Asr rescoring and confidence estimation with electra
H Futami, H Inaguma, M Mimura, S Sakai, T Kawahara
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2021
192021
ESPnet-ST IWSLT 2021 offline speech translation system
H Inaguma, B Yan, S Dalmia, P Guo, J Shi, K Duh, S Watanabe
arXiv preprint arXiv:2107.00636, 2021
192021
The system can't perform the operation now. Try again later.
Articles 1–20