Improving Streaming Transformer Based ASR Under a Framework of Self-supervised Learning

Abstract

Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then fine-tuned with limited labeled data. However, the non-streaming architecture like bidirectional transformer is usually adopted by the neural network to achieve competitive results, which can not be used in streaming scenarios. In this paper, we mainly focus on improving the performance of streaming transformer under the self-supervised learning framework. Specifically, we propose a novel two-stage training method during fine-tuning, which combines knowledge distilling and self-training. The proposed training method achieves 16.3% relative word error rate (WER) reduction on Librispeech noisy test set. Finally, by only using the 100h clean subset of Librispeech as the labeled data and the rest (860h) as the unlabeled data, our streaming transformer based model obtains competitive WERs 3.5/8.7 on Librispeech clean/noisy test sets.

arXiv commentINTERSPEECH2021

References in corpus (10)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• FitNets: Hints for Thin Deep Nets
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
• End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
• Transformers with convolutional context for ASR
• TinyBERT: Distilling BERT for Natural Language Understanding
• Self-training and Pre-training are Complementary for Speech Recognition
• Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition
• Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data