The Hitachi/JHU CHiME-5 system: Advances in speech recognition for everyday home environments using multiple microphone arrays

Kanda, Naoyuki; Ikeshita, Rintaro; Horiguchi, Shota; Fujita, Yusuke; Nagamatsu, Kenji; Wang, Xiaofei; Manohar, Vimal; Yalta Soplin, Nelson Enrique; Maciejewski, Matthew; Chen, Szu-Jui; Subramanian, Aswin Shanmugam; Li, Ruizhi; Wang, Zhiqi; Naradowsky, Jason; Garcia-Perera, L. Paola; Sell, Gregory

doi:10.21437/CHiME.2018-2

The Hitachi/JHU CHiME-5 system: Advances in speech recognition for everyday home environments using multiple microphone arrays

Naoyuki Kanda, Rintaro Ikeshita, Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu, Xiaofei Wang, Vimal Manohar, Nelson Enrique Yalta Soplin, Matthew Maciejewski, Szu-Jui Chen, Aswin Shanmugam Subramanian, Ruizhi Li, Zhiqi Wang, Jason Naradowsky, L. Paola Garcia-Perera, Gregory Sell

This paper presents Hitachi and JHU’s efforts on developing CHiME-5 system to recognize dinner party speeches recorded by multiple microphone arrays. We newly developed (1) the way to apply multiple data augmentation methods, (2) residual bidirectional long short-term memory, (3) 4-ch acoustic models, (4) multiple-array combination methods, (5) hypothesis deduplication method, and (6) speaker adaptation technique of neural beamformer. As the results, our best system in category B achieved 52.38% of word error rates (WERs) for development set, which corresponded to 35% of relative WER reduction from the state-of-the-art baseline. Our best system also achieved 48.20% of WER for evaluation set, which was the 2nd best result in the CHiME-5 competition.