• Aug 06, 2019 News!IJIEE Vol. 9, No. 3 issue has been published online!   [Click]
  • Jun 04, 2019 News!IJIEE Vol. 9, No. 2 issue has been published online!   [Click]
  • May 14, 2019 News!Vol.7, No.5-Vol.8, no.2 has been indexed by EI (Inspec).   [Click]
General Information
    • ISSN: 2010-3719 (Online)
    • Abbreviated Title: Int. J. Inf. Electron. Eng.
    • Frequency: Quarterly
    • DOI: 10.18178/IJIEE
    • Editor-in-Chief: Prof. Chandratilak De Silva Liyanage
    • Executive Editor: Jennifer Zeng
    • Abstracting/ Indexing : Google Scholar, Electronic Journals Library, Crossref and ProQuest, Ei (INSPEC, IET), EBSCO.
    • E-mail ijiee@ejournal.net
Editor-in-chief

 
University of Brunei Darussalam, Brunei Darussalam   
" It is a great honor to serve as the editor-in-chief of IJIEE. I'll work together with the editorial team. Hopefully, The value of IJIEE will be well recognized among the readers in the related field."

IJIEE 2015 Vol.5(6): 423-427 ISSN: 2010-3719
DOI: 10.7763/IJIEE.2015.V5.571

Automatic Speaker Recognition System in Adverse Conditions — Implication of Noise and Reverberation on System Performance

Khamis A. Al-Karawi, Ahmed H. Al-Noori, Francis F. Li, and Tim Ritchings
Abstract— Speaker recognition has been developed and evolved over the past few decades into a supposedly mature technique. Existing methods typically utilize robust features extracted from clean speech. In real-world applications, especially security and forensics related ones, reliability of recognition becomes crucial, meanwhile limited speech samples and adverse acoustic conditions, most notably noise and reverberation, impose further complications. This paper is presented from a study into the behavior of typical speaker recognition systems in adverse retrieval phases. Following a brief review, a speaker recognition system was implemented using the MSR Identity Toolbox by Microsoft. Validation tests were carried out with clean speech and the speech contaminated by noise and/or reverberation of varying degrees. The image source method was adopted to take into account real acoustic conditions in the spaces. Statistical relationships between recognition accuracy and signal to noise ratios or reverberation times have therefore been established. Results show noise and reverberation can, to different extents, degrade the performance of recognition. Both reverberation time and direct to reverberation ratio can affect recognition accuracy. The findings may be used to estimate the accuracy of speaker recognition and further determine the likelihood a particular speaker.

Index Terms— Clean speech, GMM-UBM, ISM, reverberation, robust speaker recognition, MFCC, MSR toolbox, noise.

The authors are with School of Computing Science and Engineering, University of Salford, UK (e-mail: k.a.yousif@edu.salford.ac.uk).

[PDF]

Cite: Khamis A. Al-Karawi, Ahmed H. Al-Noori, Francis F. Li, and Tim Ritchings, " Automatic Speaker Recognition System in Adverse Conditions — Implication of Noise and Reverberation on System Performance," International Journal of Information and Electronics Engineering vol. 5, no. 6, pp. 423-427, 2015.

Copyright © 2008-2019. International Journal of Information and Electronics Engineering. All rights reserved.
E-mail: ijiee@ejournal.net