Motoi Omachi

15 papers A 4Misc 4Journal 4Unranked 3
YearRankTypeTitle / Venue / Authors
2023 Misc conf
Align, Write, Re-Order: Explainable End-to-End Speech Translation via Operation Sequence Generation.
ICASSP
Motoi Omachi, Brian Yan, Siddharth Dalmia, Yuya Fujita, Shinji Watanabe
2022 J jnl
Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation.
CoRR
Motoi Omachi, Brian Yan, Siddharth Dalmia, Yuya Fujita, Shinji Watanabe
2022 Misc conf
Non-Autoregressive End-To-End Automatic Speech Recognition Incorporating Downstream Natural Language Processing.
ICASSP
Motoi Omachi, Yuya Fujita, Shinji Watanabe, Tianzi Wang
2021 — conf
End-to-end ASR to jointly predict transcriptions and linguistic annotations.
NAACL-HLT
Motoi Omachi, Yuya Fujita, Shinji Watanabe, Matthew Wiesner
2021 A conf
Toward Streaming ASR with Non-Autoregressive Insertion-Based Model.
Interspeech
Yuya Fujita, Tianzi Wang, Shinji Watanabe, Motoi Omachi
2020 Misc conf
Attention-Based ASR with Lightweight and Dynamic Convolutions.
ICASSP
Yuya Fujita, Aswin Shanmugam Subramanian, Motoi Omachi, Shinji Watanabe
2020 A conf
End-to-End ASR with Adaptive Span Self-Attention.
INTERSPEECH
Xuankai Chang, Aswin Shanmugam Subramanian, Pengcheng Guo, Shinji Watanabe, Yuya Fujita, Motoi Omachi
2020 A conf
Insertion-Based Modeling for End-to-End Automatic Speech Recognition.
INTERSPEECH
Yuya Fujita, Shinji Watanabe, Motoi Omachi, Xuankai Chang
2020 J jnl
Insertion-Based Modeling for End-to-End Automatic Speech Recognition.
CoRR
Yuya Fujita, Shinji Watanabe, Motoi Omachi, Xuankai Chang
2018 Misc conf
Multi Scale Feedback Connection for Noise Robust Acoustic Modeling.
ICASSP
Dung T. Tran, Ken-ichi Iso, Motoi Omachi, Yuya Fujita
2018 — conf
Speaker Selective Beamformer with Keyword Mask Estimation.
SLT
Yusuke Kida, Dung T. Tran, Motoi Omachi, Toru Taniguchi, Yuya Fujita
2018 J jnl
Speaker Selective Beamformer with Keyword Mask Estimation.
CoRR
Yusuke Kida, Dung T. Tran, Motoi Omachi, Toru Taniguchi, Yuya Fujita
2017 J jnl
Associative Memory Model-Based Linear Filtering and Its Application to Tandem Connectionist Blind Source Separation.
IEEE ACM Trans. Audio Speech Lang. Process.
Motoi Omachi, Tetsuji Ogawa, Tetsunori Kobayashi
2015 — conf
Separation matrix optimization using associative memory model for blind source separation.
EUSIPCO
Motoi Omachi, Tetsuji Ogawa, Tetsunori Kobayashi, Masaru Fujieda, Kazuhiro Katagiri
2014 A conf
Effect of frequency weighting on MLP-based speaker canonicalization.
INTERSPEECH
Yuichi Kubota, Motoi Omachi, Tetsuji Ogawa, Tetsunori Kobayashi, Tsuneo Nitta