Conference Proceeding

An approach to robust speaker recognition using stochastic matching

Inst. of Comput. Technol., Acad. Sinica, Beijing
02/2000; DOI:10.1109/ICOSP.2000.891632 ISBN: 0-7803-5747-7 pp.803 - 806 vol.2 In proceeding of: Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on, Volume: 2
Source: IEEE Xplore

ABSTRACT This paper describes an approach to robust speaker recognition
using stochastic matching for depressing channel mismatch in telephone
networks. For the two recognition algorithms such as GMM (Gaussian
mixture models) for text-independent speaker identification and HMM for
text prompted speaker verification, the corresponding stochastic
matching approaches are presented in detail. Experimental results have
shown that the stochastic matching approach for channel compensation
based on the compensation term from GMM is better than that of the
compensation term from a single Gaussian model

0 0
 · 
0 Bookmarks
 · 
13 Views
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

compensation term
 
corresponding stochastic
 
depressing channel mismatch
 
Experimental results
 
mixture models
 
single Gaussian model
 
text-independent speaker identification
 
two recognition algorithms