Minimum Latency Training of Sequence Transducers for Streaming End-to-End Speech Recognition

Yusuke Shinohara, Shinji Watanabe

研究成果査読

抄録

Sequence transducers, such as the RNN-T and the Conformer-T, are one of the most promising models of end-to-end speech recognition, especially in streaming scenarios where both latency and accuracy are important. Although various methods, such as alignment-restricted training and FastEmit, have been studied to reduce the latency, latency reduction is often accompanied with a significant degradation in accuracy. We argue that this suboptimal performance might be caused because none of the prior methods explicitly model and reduce the latency. In this paper, we propose a new training method to explicitly model and reduce the latency of sequence transducer models. First, we define the expected latency at each diagonal line on the lattice, and show that its gradient can be computed efficiently within the forward-backward algorithm. Then we augment the transducer loss with this expected latency, so that an optimal trade-off between latency and accuracy is achieved. Experimental results on the WSJ dataset show that the proposed minimum latency training reduces the latency of causal Conformer-T from 220 ms to 27 ms within a WER degradation of 0.7%, and outperforms conventional alignment-restricted training (110 ms) and FastEmit (67 ms) methods.

本文言語English
ページ(範囲)2098-2102
ページ数5
ジャーナルProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
2022-September
DOI
出版ステータスPublished - 2022
外部発表はい
イベント23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022 - Incheon, Korea, Republic of
継続期間: 2022 9月 182022 9月 22

ASJC Scopus subject areas

  • 言語および言語学
  • 人間とコンピュータの相互作用
  • 信号処理
  • ソフトウェア
  • モデリングとシミュレーション

フィンガープリント

「Minimum Latency Training of Sequence Transducers for Streaming 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