Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems

TL;DR

This paper introduces a novel contextual spelling correction model for end-to-end speech recognition that improves accuracy by effectively biasing recognition towards specific context phrases, outperforming traditional methods.

Contribution

A new domain-insensitive, sequence-to-sequence contextual biasing approach with autoregressive and non-autoregressive mechanisms for end-to-end ASR systems.

Findings

Achieves up to 51% relative WER reduction.

NAR model reduces size by 43.2% and speeds up inference by 2.1 times.

Outperforms traditional biasing methods.

Abstract

Contextual biasing is an important and challenging task for end-to-end automatic speech recognition (ASR) systems, which aims to achieve better recognition performance by biasing the ASR system to particular context phrases such as person names, music list, proper nouns, etc. Existing methods mainly include contextual LM biasing and adding bias encoder into end-to-end ASR models. In this work, we introduce a novel approach to do contextual biasing by adding a contextual spelling correction model on top of the end-to-end ASR system. We incorporate contextual information into a sequence-to-sequence spelling correction model with a shared context encoder. Our proposed model includes two different mechanisms: autoregressive (AR) and non-autoregressive (NAR). We propose filtering algorithms to handle large-size context lists, and performance balancing mechanisms to control the biasing degree of the model. We demonstrate the proposed model is a general biasing solution which is domain-insensitive and can be adopted in different scenarios. Experiments show that the proposed method achieves as much as 51% relative word error rate (WER) reduction over ASR system and outperforms traditional biasing methods. Compared to the AR solution, the proposed NAR model reduces model size by 43.2% and speeds up inference by 2.1 times.