Polyphone Disambiguation for Mandarin Chinese Using Conditional Neural Network with Multi-level Embedding Features

Cai, Zexin; Yang, Yaogen; Zhang, Chuxiong; Qin, Xiaoyi; Li, Ming

doi:10.48550/arxiv.1907.01749

Cited by 1 publication

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[8] treated polyphone disambiguation as a classification task, using a bidirectional long short-term memory (BLSTM) neural network and additional information such as part-of-speech (POS) tags to predict the pronunciation of the input polyphonic characters, which yielded good results. [9] used multi-level embedding [10] features as input and yielded improvement on the task. [11] used weighted softmax and modified focal loss to solve the problem of unbalanced training samples.…”

Section: Learning-based Approachesmentioning

confidence: 99%

Distant Supervision for Polyphone Disambiguation in Mandarin Chinese

Zhang¹,

Zhao²,

Zhu³

et al. 2020

Interspeech 2020

View full text Add to dashboard Cite

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.

show abstract