A Purely End-to-End System for Multi-speaker Speech Recognition

Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey


Abstract
Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments for effective learning. In this paper, we propose a new sequence-to-sequence framework to directly decode multiple label sequences from a single speech sequence by unifying source separation and speech recognition functions in an end-to-end manner. We further propose a new objective function to improve the contrast between the hidden vectors to avoid generating similar hypotheses. Experimental results show that the model is directly able to learn a mapping from a speech mixture to multiple label sequences, achieving 83.1% relative improvement compared to a model trained without the proposed objective. Interestingly, the results are comparable to those produced by previous end-to-end works featuring explicit separation and recognition modules.
Anthology ID:
P18-1244
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2620–2630
URL:
https://www.aclweb.org/anthology/P18-1244
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
Note:
 P18-1244.Notes.pdf
Poster:
 P18-1244.Poster.pdf