ISSN 0021-3454 (print version)
ISSN 2500-0381 (online version)
Menu

12
Issue
vol 59 / DECEMBER, 2016
Article
UDC 57.087.1

EMPLOYMENT OF DTW-BASED HMM-GMM MULTI-SESSION TRAINING IN TEXTDEPENDENT SPEAKER VERIFICATION

S. A. Novoselov
STC-Innovation Ltd., St. Petersburg; Researcher


V. A. Sukhmel
St. Petersburg State University, Department of Computer Modelling and Multiprocessor Systems; Post-Graduate Student


A. V. Sholokhov
University of Eastern Finland, Joensuu, FI-80101, Finland; postgraguate


T. . Pekhovsky
«Speech Technology Center-Innovation», Ltd.; leading scientific researcher


Abstract. An HMM training procedure using several password utterances is proposed. The proposed method is based on the Dynamic Time Warping algorithm, and is shown to allow for reduction of verification system errors.
Keywords: text-dependent speaker verification, short utterance, MFCC, HMM, GMM, DTW