A Time-Varying Adaptive IIR Filter for Robust Text-Independent Speaker Verification


IEICE TRANSACTIONS on Information and Systems   Vol.E96-D   No.3   pp.699-707
Publication Date: 2013/03/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E96.D.699
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Speech and Hearing
speaker verification,  feature smoothing,  adaptive filter,  Gaussian Mixture Model (GMM),  Support Vector Machines (SVM),  

Full Text: PDF(1022.5KB)>>
Buy this Article

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.