Improving Rare Words Recognition through Homophone Extension and Unified Writing for Low-resource Cantonese Speech Recognition
This work addresses the challenge of recognizing homophone characters and rare words in low-resource Cantonese ASR, which is an incremental improvement for speech recognition in tonal languages.
The paper tackled the problem of low-resource Cantonese speech recognition by proposing a homophone extension method and an automatic unified writing method, resulting in absolute Character Error Rate decreases of around 5% and 18% on in-domain and out-of-domain test sets.
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%.