A Simple Baseline for Domain Adaptation in End to End ASR Systems Using Synthetic Data

Abstract

Automatic Speech Recognition(ASR) has been dominated by deep learning-based end-to-end speech recognition models. These approaches require large amounts of labeled data in the form of audio-text pairs. Moreover, these models are more susceptible to domain shift as compared to traditional models. It is common practice to train generic ASR models and then adapt them to target domains using comparatively smaller data sets. We consider a more extreme case of domain adaptation where text-only corpus is available. In this work, we propose a simple baseline technique for domain adaptation in end-to-end speech recognition models. We convert the text-only corpus to audio data using single speaker Text to Speech (TTS) engine. The parallel data in the target domain is then used to fine-tune the final dense layer of generic ASR models. We show that single speaker synthetic TTS data coupled with final dense layer only fine-tuning provides reasonable improvements in word error rates. We use text data from address and e-commerce search domains to show the effectiveness of our low-cost baseline approach on CTC and attention-based models.

arXiv commentAccepted at ECNLP @ACL 2022

References in corpus (7)

• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Sequence Transduction with Recurrent Neural Networks
• Listen, Attend and Spell
• Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
• Cross-Language Transfer Learning, Continuous Learning, and Domain Adaptation for End-to-End Automatic Speech Recognition
• Attention based end to end Speech Recognition for Voice Search in Hindi and English
• Improving Performance of End-to-End ASR on Numeric Sequences

Cited by in corpus (1)

• On Comparison of Encoders for Attention based End to End Speech Recognition in Standalone and Rescoring Mode