Spoken Arabic Digits recognition using MFCC based on GMM

Author

Hammami, N. ; Bedda, M. ; Farah, Nadir

Author_Institution

Lab. LabGed, Univ. Badji Mokhtar Annaba, Annaba, Algeria

fYear

2012

fDate

6-9 Oct. 2012

Firstpage

160

Lastpage

163

Abstract

Gaussian mixture model (GMM) is a conventional method for speech recognition, known for its effectiveness and scalability in speech modeling. This paper presents automatic recognition of the Spoken Arabic Digits based on (GMM) classifier and the leading approach for speech recognition features extraction Delta-Delta Mel- frequency cepstral coefficients (DDMFCC). The experimental results give the best result with the obtained parameters; they achieve a 99.31% correct digit recognition dataset which is very satisfactory compared to previous work on spoken Arabic digits speech recognition.

Keywords

Gaussian processes; natural language processing; speech recognition; DDMFCC; GMM; Gaussian mixture model; MFCC; delta-delta mel-frequency cepstral coefficients; speech modeling; speech recognition features extraction; spoken Arabic digits speech recognition; Hidden Markov models; Mel frequency cepstral coefficient; Arabic speech recognition; Arabic spoken digits; DDMFCC; Gaussian mixture model (GMM); MFCC;

fLanguage

English

Publisher

ieee

Conference_Titel

Sustainable Utilization and Development in Engineering and Technology (STUDENT), 2012 IEEE Conference on

Conference_Location

Kuala Lumpur

ISSN

1985-5753

Print_ISBN

978-1-4673-1649-1

Electronic_ISBN

1985-5753

Type

conf

DOI

10.1109/STUDENT.2012.6408392

Filename

6408392