Automatic Arabic recognition system based on support vector machines (SVMs)

Author

Astuti, W. ; Salma, A.M. ; Aibinu, A.M. ; Akmeliawati, R. ; Salami, Momoh Jimoh E

Author_Institution

Dept. of Mechatron. Eng., Int. Islamic Univ. Malaysia, Kuala Lumpur, Malaysia

fYear

2011

fDate

19-20 Sept. 2011

Firstpage

1

Lastpage

4

Abstract

Automatic Speech Recognition (ASR) for Arabic word has been developed in this work. The system has the ability to recognize word that is uttered by the speaker. In this paper, an approach using support vector machines (SVMs) for identifying Arabic word based on the speaker speech is proposed. The proposed SVMs-based Automatic Speech Recognition system is tested experimentally using words uttered by 20 native Arabic speakers. The Mel Frequency Cepstral Coefficient (MFCC) is adopted as a feature and later used as an input to the SVM-based identifier. The performance of the proposed technique has been investigated, especially for multiclass classification and it is found to produce good accuracy within short duration training time.

Keywords

natural languages; speaker recognition; support vector machines; ASR; MFCC; SVM-based identifier; automatic Arabic recognition system; automatic speech recognition; mel frequency cepstral coefficient; multiclass classification; speaker speech; support vector machine; Feature extraction; Kernel; Mel frequency cepstral coefficient; Speech; Speech processing; Speech recognition; Support vector machines; Automatic Speech Recognition; MFCC; SVM;

fLanguage

English

Publisher

ieee

Conference_Titel

National Postgraduate Conference (NPC), 2011

Conference_Location

Kuala Lumpur

Print_ISBN

978-1-4577-1882-3

Type

conf

DOI

10.1109/NatPC.2011.6136331

Filename

6136331