A Practical Two-Stage Training Strategy for Multi-Stream End-to-End Speech Recognition

Ruizhi Li, Gregory Sell, Xiaofei Wang, Shinji Watanabe, Hynek Hermansky

研究成果: Conference contribution

3 被引用数 (Scopus)

抄録

The multi-stream paradigm of audio processing, in which several sources are simultaneously considered, has been an active research area for information fusion. Our previous study offered a promising direction within end-to-end automatic speech recognition, where parallel encoders aim to capture diverse information followed by a stream-level fusion based on attention mechanisms to combine the different views. However, with an increasing number of streams resulting in an increasing number of encoders, the previous approach could require substantial memory and massive amounts of parallel data for joint training. In this work, we propose a practical two-stage training scheme. Stage-1 is to train a Universal Feature Extractor (UFE), where encoder outputs are produced from a single-stream model trained with all data. Stage-2 formulates a multi-stream scheme intending to solely train the attention fusion module using the UFE features and pretrained components from Stage-1. Experiments have been conducted on two datasets, DIRHA and AMI, as a multi-stream scenario. Compared with our previous method, this strategy achieves relative word error rate reductions of 8.2-32.4%, while consistently outperforming several conventional combination methods.

本文言語English
ホスト出版物のタイトル2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ7014-7018
ページ数5
ISBN(電子版)9781509066315
DOI
出版ステータスPublished - 2020 5
外部発表はい
イベント2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
継続期間: 2020 5 42020 5 8

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2020-May
ISSN(印刷版)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
国/地域Spain
CityBarcelona
Period20/5/420/5/8

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「A Practical Two-Stage Training Strategy for Multi-Stream End-to-End Speech Recognition」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