Mandarin keyword spotting using syllable based confidence features and SVM

Author

Li, Haiyang ; Han, Jiqing ; Zheng, Tieran ; Zheng, Guibin

Author_Institution

Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol., Harbin, China

Volume

1

fYear

2011

fDate

25-28 July 2011

Firstpage

256

Lastpage

259

Abstract

A method for confidence measure (CM) using syllable based confidence features is proposed to improve false-alarm rejection of the mandarin keyword spotting (KWS). The features take advantage of the merit of mandarin syllable structure and describe the confidences in every sub-syllable level. The evaluation is processed with support vector machine (SVM) on telephone speech database. Compared with the typical method, the experimental results show that the proposed CM features and SVM based method yields significant improvement, and at best a reduction of 12.13% equal error rate (EER) is gotten.

Keywords

error statistics; natural languages; speech processing; support vector machines; EER; KWS; Mandarin keyword spotting; Mandarin syllable structure; SVM; confidence measure; equal error rate; false-alarm rejection; support vector machine; syllable based confidence feature; telephone speech database; Acoustics; Computational modeling; Hidden Markov models; Kernel; Speech recognition; Support vector machines; Training;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Information Processing (ICICIP), 2011 2nd International Conference on

Conference_Location

Harbin

Print_ISBN

978-1-4577-0813-8

Type

conf

DOI

10.1109/ICICIP.2011.6008243

Filename

6008243