Publications
Detail of publication
Citation
p. 425-432, Springer, Berlin, 2004. : On the background model construction for speaker verification using GMM . Text, speech and dialogue,
Download PDF
Abstract
A method of speaker verification based on Gaussian mixture models is presented in this paper. The method works with a background model which is composed of several submodels. Several different approaches for construction of the background model from the submodels are introduced here: the log likelihood of the background model is determined either as the average of the log likelihoods of the particular submodels, or a maximum from the log likelihoods of the particular submodels is selected. A large number of experiments was performed in order to find which of the approaches gives the best result. All experiments show that procedures which use a maximum of the log likelihoods of the background submodels have better performance than the procedure which uses the average log likelihood.
Detail of publication
Title: | On the background model construction for speaker verification using GMM |
---|---|
Author: | Padrta, A. ; Radová, V. |
Language: | English |
Date of publication: | 8 Sep 2004 |
Year: | 2004 |
Type of publication: | Papers in proceedings of reviewed conferences |
Title of journal or book: | Text, speech and dialogue |
Page: | 425 - 432 |
ISBN: | 3-540-23049-1 |
Publisher: | Springer |
Address: | Berlin |
Date: | 8 Sep 2004 - 11 Sep 2004 |
Keywords
speaker verification, score normalization, background model
BibTeX
@INPROCEEDINGS{PadrtaA_2004_Onthebackground, author = {Padrta, A. and Radov\'{a}, V.}, title = {On the background model construction for speaker verification using GMM}, year = {2004}, publisher = {Springer}, journal = {Text, speech and dialogue}, address = {Berlin}, pages = {425-432}, ISBN = {3-540-23049-1}, url = {http://www.kky.zcu.cz/en/publications/PadrtaA_2004_Onthebackground}, }