@inproceedings{c39b4793880e4eb697490e21e72e6642,
title = "Acoustic Modeling for Distant Multi-talker Speech Recognition with Single- and Multi-channel Branches",
abstract = "This paper presents a novel heterogeneous-input multi-channel acoustic model (AM) that has both single-channel and multi-channel input branches. In our proposed training pipeline, a single-channel AM is trained first, then a multi-channel AM is trained starting from the single-channel AM with a randomly initialized multi-channel input branch. Our model uniquely uses the power of a complemen-tal speech enhancement (SE) module while exploiting the power of jointly trained AM and SE architecture. Our method was the foundation for the Hitachi/JHU CHiME-5 system that achieved the second-best result in the CHiME-5 competition, and this paper details various investigation results that we were not able to present during the competition period. We also evaluated and reconfirmed our method's effectiveness with the AMI Meeting Corpus. Our AM achieved a 30.12% word error rate (WER) for the development set and a 32.33% WER for the evaluation set for the AMI Corpus, both of which are the best results ever reported to the best of our knowledge.",
keywords = "Acoustic model, deep learning, speech enhancement, speech recognition",
author = "Naoyuki Kanda and Yusuke Fujita and Shota Horiguchi and Rintaro Ikeshita and Kenji Nagamatsu and Shinji Watanabe",
year = "2019",
month = may,
day = "1",
doi = "10.1109/ICASSP.2019.8682273",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "6630--6634",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
note = "44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 ; Conference date: 12-05-2019 Through 17-05-2019",
}