Streaming chunk-aware multihead attention for online end-to-end speech recognition

Shiliang Zhang, Zhifu Gao, Haoneng Luo, Ming Lei, Jie Gao, Zhijie Yan, Lei Xie

科研成果: 期刊稿件会议文章同行评审

14 引用 (Scopus)

摘要

Recently, streaming end-to-end automatic speech recognition (E2E-ASR) has gained more and more attention. Many efforts have been paid to turn the non-streaming attention-based E2E-ASR system into streaming architecture. In this work, we propose a novel online E2E-ASR system by using Streaming Chunk-Aware Multihead Attention (SCAMA) and a latency control memory equipped self-attention network (LC-SAN-M). LC-SAN-M uses chunk-level input to control the latency of encoder. As to SCAMA, a jointly trained predictor is used to control the output of encoder when feeding to decoder, which enables decoder to generate output in streaming manner. Experimental results on the open 170-hour AISHELL-1 and an industrial-level 20000-hour Mandarin speech recognition tasks show that our approach can significantly outperform the MoChA-based baseline system under comparable setup. On the AISHELL-1 task, our proposed method achieves a character error rate (CER) of 7.39%, to the best of our knowledge, which is the best published performance for online ASR.

源语言英语
页(从-至)2142-2146
页数5
期刊Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
2020-October
DOI
出版状态已出版 - 2020
活动21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, 中国
期限: 25 10月 202029 10月 2020

指纹

探究 'Streaming chunk-aware multihead attention for online end-to-end speech recognition' 的科研主题。它们共同构成独一无二的指纹。

引用此