Complete recognition of continuous Mandarin speech for Chinese language with very large vocabulary using limited training data

Author

Wang, Hsin-Min ; Ho, Tai-Hsuan ; Yang, Rung-Chiung ; Shen, Jia-Lin ; Bai, Bo-Ren ; Hong, Jenn-Chau ; Chen, Wei-Peng ; Yu, Tong-Lo ; Lee, Lin-shan

Author_Institution

Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan

Volume

5

Issue

2

fYear

1997

fDate

3/1/1997 12:00:00 AM

Firstpage

195

Lastpage

200

Abstract

This correspondence presents the first known results of complete recognition of continuous Mandarin speech for the Chinese language with very large vocabulary but very limited training data. Various acoustic and linguistic processing techniques were developed, and a prototype system of a continuous speech Mandarin dictation machine has been successfully implemented. The best recognition accuracy achieved is 92.2% for finally decoded Chinese characters

Keywords

dictation; linguistics; pattern recognition equipment; speech recognition; speech recognition equipment; Chinese language; acoustic processing techniques; complete recognition; continuous Mandarin speech; dictation machine; finally decoded Chinese characters; linguistic processing techniques; prototype system; recognition accuracy; training data; very large vocabulary; Character recognition; Computer science; Decoding; Hidden Markov models; Natural languages; Prototypes; Speech processing; Speech recognition; Training data; Vocabulary;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.554782

Filename

554782