A Method of Part of Speech Based on the Algorithm of C4.5 for Polyphone

Author

Peng Fuming ; He Xin ; Shi Yingchun

Author_Institution

Sch. of Autom., Nanjing Univ. of Sci. & Technol., Nanjing, China

fYear

2012

fDate

2-4 Nov. 2012

Firstpage

673

Lastpage

676

Abstract

Chinese is one of graceful languages, not only it´s hieroglyphic writing, but also one of flexible languages, which can describe a thing or sensation of people visually. This is because of polyphone, which exists in Chinese. But it´s also because of polyphone, there are some difficult in Chinese speech synthesis, especially in the conversion between character and pronunciation. Polyphone is a large proportion in Chinese, so the problem of polyphone is the key in the module of character-pronunciation conversion. In this paper, the part of speech rules is presented to solve the problem of polyphone, which is based on the algorithm of C4.5. And experiment results presented to prove the effectiveness of this method.

Keywords

natural language processing; speech synthesis; C4.5 algorithm; Chinese language; Chinese speech synthesis; character-pronunciation conversion; flexible languages; hieroglyphic writing; part of speech; polyphone; Classification algorithms; Decision trees; Educational institutions; Speech; Training; Training data; Vocabulary; polyphone; part of speech(POS); C4.5;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Information Networking and Security (MINES), 2012 Fourth International Conference on

Conference_Location

Nanjing

Print_ISBN

978-1-4673-3093-0

Type

conf

DOI

10.1109/MINES.2012.28

Filename

6407400