Hiroshi Seki
Hiroshi Seki
Unknown affiliation
No verified email
Title
Cited by
Cited by
Year
A purely end-to-end system for multi-speaker speech recognition
H Seki, T Hori, S Watanabe, JL Roux, JR Hershey
arXiv preprint arXiv:1805.05826, 2018
442018
An end-to-end language-tracking speech recognizer for mixed-language speech
H Seki, S Watanabe, T Hori, J Le Roux, JR Hershey
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
292018
A deep neural network integrated with filterbank learning for speech recognition
H Seki, K Yamamoto, S Nakagawa
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
282017
Robust lecture speech translation for speech misrecognition and its rescoring effect from multiple candidates
K Sahashi, N Goto, H Seki, K Yamamoto, T Akiba, S Nakagawa
2017 International Conference on Advanced Informatics, Concepts, Theory, and …, 2017
2017
話者クラスタリングに基づく短時間発話音声認識
関博史, 榎並大介, 朱発強, 山本一公, 中川聖一
電子情報通信学会論文誌 D 100 (1), 81-92, 2017
2017
The system can't perform the operation now. Try again later.
Articles 1–5