Comparative study of hybrid models for robust speaker recognition task
Joint Authors
Zergat, Kawthar Yasamin
Amrouche, Abd al-Rahman
Source
Issue
Vol. 20, Issue 2 (31 Dec. 2013), pp.1-8, 8 p.
Publisher
Research Centre for Scientific and Technical Information
Publication Date
2013-12-31
Country of Publication
Algeria
No. of Pages
8
Main Subjects
Abstract EN
This paper deals with text-independent speaker verification system based on spoken Arabic digits in real environment.
In this work, we adopted Mel-Frequency Cepstral Coefficients (MFCC) as the speaker speech feature parameters, Gaussian Mixture Model (GMM) are used for modeling the extracted speech feature and training the support vector machines (SVMs).
The experiments were conducted on the ARADIGIT database at different Signal-to-Noise Ratio (SNR) levels and under two noisy conditions issued from NOISEX-92 database.
The obtained results show that the GMM-SVM model outperforms the GMM-UBM, especially in noisy environments.
American Psychological Association (APA)
Zergat, Kawthar Yasamin& Amrouche, Abd al-Rahman. 2013. Comparative study of hybrid models for robust speaker recognition task. RIST،Vol. 20, no. 2, pp.1-8.
https://search.emarefa.net/detail/BIM-427212
Modern Language Association (MLA)
Zergat, Kawthar Yasamin& Amrouche, Abd al-Rahman. Comparative study of hybrid models for robust speaker recognition task. RIST Vol. 20, no. 2 (2013), pp.1-8.
https://search.emarefa.net/detail/BIM-427212
American Medical Association (AMA)
Zergat, Kawthar Yasamin& Amrouche, Abd al-Rahman. Comparative study of hybrid models for robust speaker recognition task. RIST. 2013. Vol. 20, no. 2, pp.1-8.
https://search.emarefa.net/detail/BIM-427212
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-427212