End-to-end Monaural Multi-speaker ASR System without Pretraining

Xuankai Chang, Yanmin Qian, Kai Yu, Shinji Watanabe

研究成果: Conference contribution

12 被引用数 (Scopus)

抄録

Recently, end-to-end models have become a popular approach as an alternative to traditional hybrid models in automatic speech recognition (ASR). The multi-speaker speech separation and recognition task is a central task in cocktail party problem. In this paper, we present a state-of-the-art monaural multi-speaker end-to-end automatic speech recognition model. In contrast to previous studies on the monaural multi-speaker speech recognition, this end-to-end framework is trained to recognize multiple label sequences completely from scratch. The system only requires the speech mixture and corresponding label sequences, without needing any indeterminate supervisions obtained from non-mixture speech or corresponding labels/alignments. Moreover, we exploited using the individual attention module for each separated speaker and the scheduled sampling to further improve the performance. Finally, we evaluate the proposed model on the 2-speaker mixed speech generated from the WSJ corpus and the wsj0-2mix dataset, which is a speech separation and recognition benchmark. The experiments demonstrate that the proposed methods can improve the performance of the end-to-end model in separating the overlapping speech and recognizing the separated streams. From the results, the proposed model leads to ∼ 10.0% relative performance gains in terms of CER and WER respectively.

本文言語English
ホスト出版物のタイトル2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ6256-6260
ページ数5
ISBN(電子版)9781479981311
DOI
出版ステータスPublished - 2019 5
外部発表はい
イベント44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
継続期間: 2019 5 122019 5 17

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2019-May
ISSN(印刷版)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period19/5/1219/5/17

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

フィンガープリント 「End-to-end Monaural Multi-speaker ASR System without Pretraining」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル