Task-specific adaptation in Chinese name recognition

Author

Ding, Guo-Hong ; Xu, Bo ; Wang, Xia ; Cao, Yang ; Ding, Feng ; Tang, Yuezhong

Author_Institution

Nokia Res. Center, Beijing, China

fYear

2004

fDate

15-18 Dec. 2004

Firstpage

261

Lastpage

264

Abstract

In this paper, task-specific adaptation is proposed to improve Chinese name recognition performance. Since acoustic models are usually trained using large vocabulary continuous speech corpora, there exists distortion between modeling and decoding in name recognition. To compensate the mismatch, task-specific adaptation, which is performed in the MLLR framework with multi-regression classes, is proposed. Experimental results show that task-specific adaptation is very effective in Chinese name recognition to compensate the mismatch.

Keywords

mobile radio; regression analysis; speech processing; speech recognition; telephony; vocabulary; Chinese name recognition; MLLR framework; acoustic model training; decoding; large vocabulary continuous speech corpora; multi-regression classes; performance; task-specific adaptation; Acoustic distortion; Databases; Decoding; Loudspeakers; Maximum likelihood linear regression; Pattern recognition; Speech analysis; Speech recognition; Technological innovation; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Chinese Spoken Language Processing, 2004 International Symposium on

Print_ISBN

0-7803-8678-7

Type

conf

DOI

10.1109/CHINSL.2004.1409636

Filename

1409636

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=430206