@inproceedings{e6b23c7b88d44eeea91821de54f94ce3,
title = "A bi-directional LSTM approach for polyphone disambiguation in Mandarin Chinese",
abstract = "Polyphone disambiguation in Mandarin Chinese aims to pick up the correct pronunciation from several candidates for a polyphonic character. It serves as an essential component in human language technologies such as text-to-speech synthesis. Since the pronunciation for most polyphonic characters can be easily decided from their contexts in the text, in this paper, we address the polyphone disambiguation problem as a sequential labeling task. Specifically, we propose to use bidirectional long short-term memory (BLSTM) neural network to encode both the past and future observations on the character sequence as its inputs and predict the pronunciations. We also empirically study the impacts of (1) modeling different length of contexts, (2) the number of BLSTM layers and (3) the granularity of part-o-speech (POS) tags as features. Our results show that using a deep BLSTM is able to achieve state-of-the-art performance in polyphone disambiguation.",
keywords = "Bi-directional LSTM, Grapheme-to-phoneme conversion, Polyphone disambiguation, Sequence tagging, Text-to-Speech",
author = "Changhao Shan and Lei Xie and Kaisheng Yao",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016 ; Conference date: 17-10-2016 Through 20-10-2016",
year = "2017",
month = may,
day = "2",
doi = "10.1109/ISCSLP.2016.7918392",
language = "英语",
series = "Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Hsin-Min Wang and Qingzhi Hou and Yuan Wei and Tan Lee and Jianguo Wei and Lei Xie and Hui Feng and Jianwu Dang and Jianwu Dang",
booktitle = "Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016",
}