Motoi Omachi

Most-cited papers

Insertion-Based Modeling for End-to-End Automatic Speech Recognition
Yuya Fujita, Shinji Watanabe, Motoi Omachi, Xuan-Kai Chang
2020Interspeech35 citations Open access
Semantic Scholar
Attention-Based ASR with Lightweight and Dynamic Convolutions
Yuya Fujita, A. Subramanian, Motoi Omachi, Shinji Watanabe
2019IEEE International Conference on Acoustics, Speech, and Signal Processing18 citations
Semantic Scholar
End-to-End ASR with Adaptive Span Self-Attention
Xuan-Kai Chang, A. Subramanian, Pengcheng Guo, Shinji Watanabe +2 more
2020Interspeech16 citations
Semantic Scholar
End-to-end ASR to jointly predict transcriptions and linguistic annotations
Motoi Omachi, Yuya Fujita, Shinji Watanabe, Matthew Wiesner
2021North American Chapter of the Association for Computational Linguistics15 citations Open access
Semantic Scholar
Non-Autoregressive End-To-End Automatic Speech Recognition Incorporating Downstream Natural Language Processing
Motoi Omachi, Yuya Fujita, Shinji Watanabe, Tian-Zi Wang
2022IEEE International Conference on Acoustics, Speech, and Signal Processing8 citations
Semantic Scholar
Align, Write, Re-Order: Explainable End-to-End Speech Translation via Operation Sequence Generation
Motoi Omachi, Brian Yan, Siddharth Dalmia, Yuya Fujita +1 more
2022IEEE International Conference on Acoustics, Speech, and Signal Processing6 citations Open access
Semantic Scholar
Toward Streaming ASR with Non-Autoregressive Insertion-Based Model
Yuya Fujita, Tian-Zi Wang, Shinji Watanabe, Motoi Omachi
2020Interspeech5 citations
Semantic Scholar
Associative Memory Model-Based Linear Filtering and Its Application to Tandem Connectionist Blind Source Separation
Motoi Omachi, Tetsuji Ogawa, Tetsunori Kobayashi
2017IEEE/ACM Transactions on Audio Speech and Language Processing5 citations
Semantic Scholar
Speaker Selective Beamformer with Keyword Mask Estimation
Yusuke Kida, D. Tran, Motoi Omachi, T. Taniguchi +1 more
2018Spoken Language Technology Workshop3 citations Open access
Semantic Scholar
END-TO-END ASR AND AUDIO SEGMENTATION WITH NON-AUTOREGRESSIVE INSERTION-BASED MODEL
Yuya Fujita, Shinji Watanabe, Motoi Omachi
20202 citations
Semantic Scholar
Separation matrix optimization using associative memory model for blind source separation
Motoi Omachi, Tetsuji Ogawa, Tetsunori Kobayashi, Masaru Fujieda +1 more
2015European Signal Processing Conference1 citations
Semantic Scholar
Multi Scale Feedback Connection for Noise Robust Acoustic Modeling
D. Tran, K. Iso, Motoi Omachi, Yuya Fujita
2018IEEE International Conference on Acoustics, Speech, and Signal Processing0 citations
Semantic Scholar
Effect of frequency weighting on MLP-based speaker canonicalization
Yuichi Kubota, Motoi Omachi, Tetsuji Ogawa, Tetsunori Kobayashi +1 more
2014Interspeech0 citations
Semantic Scholar