Contribution of prosodic and cepstral features in improvment of a synthesized arabic speaker recognition task performance

Kawthar Yasmine Zergat, Abderrahmane Amrouche, Montadar Abas Taher, Nasharuddin Zainal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

An emerging need for biometric Speaker Verification (SV) and Identification (SI) systems is necessary for wireless remote access security in goal to be less vulnerable against distortion due to speech coding. This paper presents results on recognition system performed on the decoded speech of the G.729 codec. To show the performance loss due to distortion in the decoding process step, we are oriented to exploit the information contained within the source and the vocal tract resources. For this, SVM-based text-independent speaker classification was designed to use the information that combines the Mel Frequency Cepstral Coefficients (MFCC) features, the Energy, and the Pitch frequency. Experiments were performed over the Arabic spoken digits, the ARADIGIT database. The obtained results show that the best performance of Speaker recognition using G.729 decoded database is obtained by the combination of the prosodic features with an EER equal to 4,22%.

Original languageEnglish
Title of host publicationProceeding - 2013 IEEE Student Conference on Research and Development, SCOReD 2013
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages70-73
Number of pages4
ISBN (Print)9781479926565
DOIs
Publication statusPublished - 6 Jan 2015
Event2013 11th IEEE Student Conference on Research and Development, SCOReD 2013 - Putrajaya
Duration: 16 Dec 201317 Dec 2013

Other

Other2013 11th IEEE Student Conference on Research and Development, SCOReD 2013
CityPutrajaya
Period16/12/1317/12/13

Fingerprint

Speech coding
Biometrics
Decoding
Identification (control systems)
Experiments

Keywords

  • Energy
  • G.729
  • MFCC
  • Pitch
  • Speaker Recognition
  • Speech coding
  • Support Vector Machines
  • VoIP

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Biomedical Engineering
  • Electrical and Electronic Engineering

Cite this

Zergat, K. Y., Amrouche, A., Taher, M. A., & Zainal, N. (2015). Contribution of prosodic and cepstral features in improvment of a synthesized arabic speaker recognition task performance. In Proceeding - 2013 IEEE Student Conference on Research and Development, SCOReD 2013 (pp. 70-73). [7002544] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SCOReD.2013.7002544

Contribution of prosodic and cepstral features in improvment of a synthesized arabic speaker recognition task performance. / Zergat, Kawthar Yasmine; Amrouche, Abderrahmane; Taher, Montadar Abas; Zainal, Nasharuddin.

Proceeding - 2013 IEEE Student Conference on Research and Development, SCOReD 2013. Institute of Electrical and Electronics Engineers Inc., 2015. p. 70-73 7002544.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zergat, KY, Amrouche, A, Taher, MA & Zainal, N 2015, Contribution of prosodic and cepstral features in improvment of a synthesized arabic speaker recognition task performance. in Proceeding - 2013 IEEE Student Conference on Research and Development, SCOReD 2013., 7002544, Institute of Electrical and Electronics Engineers Inc., pp. 70-73, 2013 11th IEEE Student Conference on Research and Development, SCOReD 2013, Putrajaya, 16/12/13. https://doi.org/10.1109/SCOReD.2013.7002544
Zergat KY, Amrouche A, Taher MA, Zainal N. Contribution of prosodic and cepstral features in improvment of a synthesized arabic speaker recognition task performance. In Proceeding - 2013 IEEE Student Conference on Research and Development, SCOReD 2013. Institute of Electrical and Electronics Engineers Inc. 2015. p. 70-73. 7002544 https://doi.org/10.1109/SCOReD.2013.7002544
Zergat, Kawthar Yasmine ; Amrouche, Abderrahmane ; Taher, Montadar Abas ; Zainal, Nasharuddin. / Contribution of prosodic and cepstral features in improvment of a synthesized arabic speaker recognition task performance. Proceeding - 2013 IEEE Student Conference on Research and Development, SCOReD 2013. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 70-73
@inproceedings{12cd5941a21d4dcaa7ff1739bb5c6f3a,
title = "Contribution of prosodic and cepstral features in improvment of a synthesized arabic speaker recognition task performance",
abstract = "An emerging need for biometric Speaker Verification (SV) and Identification (SI) systems is necessary for wireless remote access security in goal to be less vulnerable against distortion due to speech coding. This paper presents results on recognition system performed on the decoded speech of the G.729 codec. To show the performance loss due to distortion in the decoding process step, we are oriented to exploit the information contained within the source and the vocal tract resources. For this, SVM-based text-independent speaker classification was designed to use the information that combines the Mel Frequency Cepstral Coefficients (MFCC) features, the Energy, and the Pitch frequency. Experiments were performed over the Arabic spoken digits, the ARADIGIT database. The obtained results show that the best performance of Speaker recognition using G.729 decoded database is obtained by the combination of the prosodic features with an EER equal to 4,22{\%}.",
keywords = "Energy, G.729, MFCC, Pitch, Speaker Recognition, Speech coding, Support Vector Machines, VoIP",
author = "Zergat, {Kawthar Yasmine} and Abderrahmane Amrouche and Taher, {Montadar Abas} and Nasharuddin Zainal",
year = "2015",
month = "1",
day = "6",
doi = "10.1109/SCOReD.2013.7002544",
language = "English",
isbn = "9781479926565",
pages = "70--73",
booktitle = "Proceeding - 2013 IEEE Student Conference on Research and Development, SCOReD 2013",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Contribution of prosodic and cepstral features in improvment of a synthesized arabic speaker recognition task performance

AU - Zergat, Kawthar Yasmine

AU - Amrouche, Abderrahmane

AU - Taher, Montadar Abas

AU - Zainal, Nasharuddin

PY - 2015/1/6

Y1 - 2015/1/6

N2 - An emerging need for biometric Speaker Verification (SV) and Identification (SI) systems is necessary for wireless remote access security in goal to be less vulnerable against distortion due to speech coding. This paper presents results on recognition system performed on the decoded speech of the G.729 codec. To show the performance loss due to distortion in the decoding process step, we are oriented to exploit the information contained within the source and the vocal tract resources. For this, SVM-based text-independent speaker classification was designed to use the information that combines the Mel Frequency Cepstral Coefficients (MFCC) features, the Energy, and the Pitch frequency. Experiments were performed over the Arabic spoken digits, the ARADIGIT database. The obtained results show that the best performance of Speaker recognition using G.729 decoded database is obtained by the combination of the prosodic features with an EER equal to 4,22%.

AB - An emerging need for biometric Speaker Verification (SV) and Identification (SI) systems is necessary for wireless remote access security in goal to be less vulnerable against distortion due to speech coding. This paper presents results on recognition system performed on the decoded speech of the G.729 codec. To show the performance loss due to distortion in the decoding process step, we are oriented to exploit the information contained within the source and the vocal tract resources. For this, SVM-based text-independent speaker classification was designed to use the information that combines the Mel Frequency Cepstral Coefficients (MFCC) features, the Energy, and the Pitch frequency. Experiments were performed over the Arabic spoken digits, the ARADIGIT database. The obtained results show that the best performance of Speaker recognition using G.729 decoded database is obtained by the combination of the prosodic features with an EER equal to 4,22%.

KW - Energy

KW - G.729

KW - MFCC

KW - Pitch

KW - Speaker Recognition

KW - Speech coding

KW - Support Vector Machines

KW - VoIP

UR - http://www.scopus.com/inward/record.url?scp=84921798681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921798681&partnerID=8YFLogxK

U2 - 10.1109/SCOReD.2013.7002544

DO - 10.1109/SCOReD.2013.7002544

M3 - Conference contribution

AN - SCOPUS:84921798681

SN - 9781479926565

SP - 70

EP - 73

BT - Proceeding - 2013 IEEE Student Conference on Research and Development, SCOReD 2013

PB - Institute of Electrical and Electronics Engineers Inc.

ER -