Tone recognition for Chinese speech: A comparative study of Mandarin and Cantonese

被引：0

作者：

Peng, G ^{[1
]}

Zheng, HY ^{[1
]}

Wang, WSY ^{[1
]}

机构：

[1] City Univ Hong Kong, Dept Elect Engn, Kowloon, Hong Kong, Peoples R China

来源：

2004 INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS | 2004年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a comparative study on automatic continuous tone recognition for Mandarin and Cantonese. Compared with Mandarin, Cantonese has a much more complex tone system. The effects of F-0 normalization on tone recognition of Mandarin and Cantonese will be studied. Furthermore, the two tone systems will be compared from an engineering point of view. Tone recognition accuracies of 71.50% and 83.06% have been obtained for Cantonese and Mandarin respectively. These results compare favorably with results reported for other tone recognition experiments on the same (for Cantonese) and similar databases (for Man-darin).

引用

页码：233 / 236

页数：4

共 9 条

[1]

Cao Y, 2000, INT CONF ACOUST SPEE, P1759, DOI 10.1109/ICASSP.2000.862093

[2]

CHEN SH, 1995, IEEE T SPEECH AUDI P, V3, P146

[3]

JOHN C, 1990, INTRO PHONETIC PHONO

[4] Spoken language resources for Cantonese speech processing [J].

Lee, T ;

Lo, WK ;

Ching, PC ;

Meng, H .

SPEECH COMMUNICATION, 2002, 36 (3-4) :327-342

[5]

LIU J, 2001, THESIS CITY U HONG K

[6]

PENG G, IN PRESS SPEECH COMM

[7] Classification of Thai tone sequences in syllable-segmented speech using the analysis-by-synthesis method [J].

Potisuk, S ;

Harper, MP ;

Gandour, J .

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1999, 7 (01) :95-102

[8]

WANG RH, 1999, P OR COCOSDA WORKSH, P41

[9]

WANG WSY, 1963, J SPEECH HEAR RES, V10, P629

← 1 →