Improving Rare Words Recognition through Homophone Extension and Unified Writing for Low-resource Cantonese Speech Recognition

TL;DR

This paper introduces homophone extension and unified writing methods to improve low-resource Cantonese speech recognition, significantly reducing character error rates by leveraging homophone knowledge and standardized character merging.

Contribution

It presents novel homophone extension and unified writing techniques that enhance recognition accuracy in low-resource Cantonese ASR systems.

Findings

CER decreased by around 5% with homophone extension

CER decreased by around 18% with unified writing

Both methods significantly improve recognition on diverse test sets

Abstract

Homophone characters are common in tonal syllable-based languages, such as Mandarin and Cantonese. The data-intensive end-to-end Automatic Speech Recognition (ASR) systems are more likely to mis-recognize homophone characters and rare words under low-resource settings. For the problem of lowresource Cantonese speech recognition, this paper presents a novel homophone extension method to integrate human knowledge of the homophone lexicon into the beam search decoding process with language model re-scoring. Besides, we propose an automatic unified writing method to merge the variants of Cantonese characters and standardize speech annotation guidelines, which enables more efficient utilization of labeled utterances by providing more samples for the merged characters. We empirically show that both homophone extension and unified writing improve the recognition performance significantly on both in-domain and out-of-domain test sets, with an absolute Character Error Rate (CER) decrease of around 5% and 18%.