Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies

TL;DR

This paper introduces revision strategies for causal Transformer-based ASR models to improve performance without increasing latency, achieving competitive results on Librispeech datasets.

Contribution

It proposes real-time encoder state revision and CTC spike alignment decoding to enhance causal ASR models without additional latency.

Findings

Achieved 3.7/9.2 WERs on Librispeech test sets

Outperformed traditional look-ahead and chunk-based methods

Maintained low latency with improved accuracy

Abstract

There is often a trade-off between performance and latency in streaming automatic speech recognition (ASR). Traditional methods such as look-ahead and chunk-based methods, usually require information from future frames to advance recognition accuracy, which incurs inevitable latency even if the computation is fast enough. A causal model that computes without any future frames can avoid this latency, but its performance is significantly worse than traditional methods. In this paper, we propose corresponding revision strategies to improve the causal model. Firstly, we introduce a real-time encoder states revision strategy to modify previous states. Encoder forward computation starts once the data is received and revises the previous encoder states after several frames, which is no need to wait for any right context. Furthermore, a CTC spike position alignment decoding algorithm is designed to reduce time costs brought by the revision strategy. Experiments are all conducted on Librispeech datasets. Fine-tuning on the CTC-based wav2vec2.0 model, our best method can achieve 3.7/9.2 WERs on test-clean/other sets, which is also competitive with the chunk-based methods and the knowledge distillation methods.