Using information theoretic vector quantization for inverted MFCC based speaker verification

Memon, S, Lech, M and He, L 2009, 'Using information theoretic vector quantization for inverted MFCC based speaker verification', in Proceedings of the 2nd International Conference on Computer, Control and Communication (IEEE-IC4 2009), Karachi, Pakistan, 17-18 Feb 2009, pp. 1-5.


Document type: Conference Paper
Collection: Conference Papers

Title Using information theoretic vector quantization for inverted MFCC based speaker verification
Author(s) Memon, S
Lech, M
He, L
Year 2009
Conference name 2nd International Conference on Computer, Control and Communication (IEEE-IC4 2009)
Conference location Karachi, Pakistan
Conference dates 17-18 Feb 2009
Proceedings title Proceedings of the 2nd International Conference on Computer, Control and Communication (IEEE-IC4 2009)
Publisher IEEE
Place of publication USA
Start page 1
End page 5
Total pages 5
Abstract Over the recent years different versions the GMM classifier combined with the MFCC features have been established as speaker verification benchmarks. Although highly efficient, these systems suffer from computational complexity and occasional convergence problems. In this study a search of alternative classification and feature extraction methods of similar classification efficiency but overcoming some of the problems of the classical methods was undertaken. Preliminary results obtained for two different classification methods: the classical GMM and the ITVQ and three different feature extraction methods: MFCC, IMFCC and the MFCC/IMFCC fusion are presented. The ITVQ did not show better results compare to the classical GMM classifier, however the EER increase in case for the ITVQ was only by 0.2%. The best feature extraction method was proven to be the MFCC/IMFCC fusion. Both the MFCC/IMFCC fusion and the IMFCC outperformed the classical MFCC method.
Subjects Signal Processing
Keyword(s) ITVQ
Information Theory
MFCC and IMFCC
Copyright notice ©2009 IEEE.
ISBN 9781424433148
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 12 times in Scopus Article | Citations
Access Statistics: 188 Abstract Views  -  Detailed Statistics
Created: Fri, 07 Oct 2011, 07:50:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us