A Polyphone BERT for Polyphone Disambiguation in Mandarin Chinese

TL;DR

This paper introduces a specialized BERT model for Mandarin Chinese polyphone disambiguation, significantly improving pronunciation prediction accuracy in G2P conversion for TTS systems.

Contribution

It extends pre-trained Chinese BERT with new tokens for monophonic characters, turning disambiguation into a pre-training task, and achieves state-of-the-art accuracy.

Findings

Achieved 94.1% accuracy, a 2% improvement over previous models.

Created 741 new monophonic characters for model training.

Demonstrated effectiveness of the polyphone BERT in disambiguation tasks.

Abstract

Grapheme-to-phoneme (G2P) conversion is an indispensable part of the Chinese Mandarin text-to-speech (TTS) system, and the core of G2P conversion is to solve the problem of polyphone disambiguation, which is to pick up the correct pronunciation for several candidates for a Chinese polyphonic character. In this paper, we propose a Chinese polyphone BERT model to predict the pronunciations of Chinese polyphonic characters. Firstly, we create 741 new Chinese monophonic characters from 354 source Chinese polyphonic characters by pronunciation. Then we get a Chinese polyphone BERT by extending a pre-trained Chinese BERT with 741 new Chinese monophonic characters and adding a corresponding embedding layer for new tokens, which is initialized by the embeddings of source Chinese polyphonic characters. In this way, we can turn the polyphone disambiguation task into a pre-training task of the Chinese polyphone BERT. Experimental results demonstrate the effectiveness of the proposed model, and the polyphone BERT model obtain 2% (from 92.1% to 94.1%) improvement of average accuracy compared with the BERT-based classifier model, which is the prior state-of-the-art in polyphone disambiguation.