A time-varying adaptive IIR filter for robust text-independent speaker verification
Journal article
Authors/Editors
Strategic Research Themes
No matching items found.
Publication Details
Author list: Nuratch S., Boonpramuk P., Wutiwiwatchai C.
Publisher: Institute of Electronics, Information and Communication Engineers
Publication year: 2013
Journal: IEICE Transactions on Information and Systems (0916-8532)
Volume number: E96-D
Issue number: 3
Start page: 699
End page: 707
Number of pages: 9
ISSN: 0916-8532
eISSN: 1745-1361
Languages: English-Great Britain (EN-GB)
View in Web of Science | View on publisher site | View citing articles in Web of Science
Abstract
This paper presents a new technique to smooth speech feature vectors for text-independent speaker verification using an adaptive band-pass IIR filer. The filter is designed by considering the probability density of modulation-frequency components of an M-dimensional feature vector. Each dimension of the feature vector is processed and filtered separately. Initial filter parameters, low-cut-off and high-cut-off frequencies, are first determined by the global mean of the probability densities computed from all feature vectors of a given speech utterance. Then, the cut-off frequencies are adapted over time, i.e. every frame vector, in both low-frequency and high-frequency bands based also on the global mean and the standard deviation of feature vectors. The filtered feature vectors are used in a SVM-GMM Supervector speaker verification system. The NIST Speaker Recognition Evaluation 2006 (SRE06) core-test is used in evaluation. Experimental results show that the proposed technique clearly outperforms a baseline system using a conventional RelAtive SpecTrA (RASTA) filter. Copyright ฉ 2013 The Institute of Electronics, Information and Communication Engineers.
Keywords
Adaptive filter, Feature smoothing, Gaussian mixture model (GMM), Speaker verification, Support vector machines (SVM)
Contact Information