Paper Title:
Polyphone Disambiguation Based on Maximum Entropy Model in Mandarin Grapheme-to-Phoneme Conversion
  Abstract

Polyphone disambiguation is the core issue of the grapheme-to-phoneme (G2P) conversion in Mandarin Text-to-Speech (TTS) system. In this paper, we propose a maximum entropy (ME) model to disambiguate polyphones, and evaluate various keyword selection approaches in different domains. Furthermore, we design a hierarchical clustering algorithm for automatic generation of feature templates, which minimizes the need for human supervision during ME model training. Results of comparative experiments show that, for the task of polyphone disambiguation, ME model obviously outperforms decision tree (DT), log-likelihood ratio is the best scoring measure of keyword selection, compared to manual templates, templates automatically generated by our hierarchical clustering algorithm significantly improve the accuracy of polyphone disambiguation, and greatly reduce the size of the ME model.

  Info
Periodical
Key Engineering Materials (Volumes 480-481)
Edited by
Yanwen Wu
Pages
1043-1048
DOI
10.4028/www.scientific.net/KEM.480-481.1043
Citation
F. Z. Liu, Y. Zhou, "Polyphone Disambiguation Based on Maximum Entropy Model in Mandarin Grapheme-to-Phoneme Conversion", Key Engineering Materials, Vols. 480-481, pp. 1043-1048, 2011
Online since
June 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Bin Liu, Kai Yong Jiang
Abstract:According to mesh reconstruction problem of point cloud models with similar topological structure, a mesh reconstruction algorithm of point...
209
Authors: Yi Yong Yao, Li Ping Zhao
Abstract:Aiming at the hierarchical and modularization characteristics of OLED (Organic Light Emitting Display) unit, based on the analysis of...
1168
Authors: Yan Dong, Yong Sheng Zhu, Qiang Li
Chapter 18: Mechanical and Electronic Engineering Control
Abstract:The information capacity of the characters on the license plate images affects the accuracy of recognition directly. To improve the...
7067
Authors: Rui Song Jiang, Xin Fa Chen, Da Yong Feng, Feng Jun Wang
Abstract:In this study, a novel structure design method based on knowledge template was prompted. The notion and construction methods of knowledge...
18
  | Authors: Jin Liang Bian
Chapter 1: Computer Network and Communication Engineering
Abstract:With the Internet spread and deepening of the application, the development of enterprises Internet and e-commerce business has become an...
38