Nonspecific Speech Recognition Based on HMM/LVQ Hybrid Network

Author

Shuling, Liang ; Chaoli, Wang ; Du Jiaming

Author_Institution

Sch. of Opt.-Electr. & Comput. Eng., Univ. of Shanghai for Sci. & Technol., Shanghai, China

Volume

1

fYear

2009

fDate

10-11 Oct. 2009

Firstpage

645

Lastpage

648

Abstract

A novel method of speech recognition, which is based on HMM/LVQ1-LVQ2, is proposed in this paper. First, the MFCC, DeltaMFCC and DeltaDeltaMFCC extraction algorithms are introduced, then these coefficients are normalized by HMM-based Viterbi method, after that, the normalized feature sequences are got. The recognition is first to learn coarsely by using LVQ1 and then to learn finely by LVQ2. Finally the result is given, which shows the proposed algorithm improves the recognition rates effectively, in comparison with HMM used alone or LVQ1-LVQ2 hybrid network recognition, especially for nonspecific speech.

Keywords

hidden Markov models; learning (artificial intelligence); speech recognition; vector quantisation; HMM-based Viterbi method; HMM/LVQ hybrid network; hidden Markov modeling; learning vector quantization; nonspecific speech recognition; normalized feature sequence; Computer networks; Feature extraction; Hidden Markov models; Intelligent robots; Mel frequency cepstral coefficient; Optical computing; Optical fiber networks; Optical saturation; Speech recognition; Viterbi algorithm; HMM normalization; LVQ; MFCC; Viterbi algorithm; speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computation Technology and Automation, 2009. ICICTA '09. Second International Conference on

Conference_Location

Changsha, Hunan

Print_ISBN

978-0-7695-3804-4

Type

conf

DOI

10.1109/ICICTA.2009.161

Filename

5287568