A new speaker verification algorithm based on identification results

dc.contributor.author	Khettaoui, Billal
dc.contributor.author	Dahimene, Abdelhakim
dc.date.accessioned	2021-03-25T06:41:19Z
dc.date.available	2021-03-25T06:41:19Z
dc.date.issued	2017
dc.description.abstract	In this paper, a text independent speaker recognition system based on Gaussian mixture models (GMM) was developed with a specific focus on the use of a voice activated detector (VAD) algorithm in the training and testing. At the training level, a modified estimation/maximization (EM) algorithm is used. It is less prone to get trapped around a local maximum and so, it will have more chance to converge to the global maximum of the model. A new method of background speaker's model selection based on prior knowledge of the identification results is developed	en_US
dc.identifier.isbn	978-1-5386-0687-2
dc.identifier.isbn	Electronic ISBN:978-1-5386-0686-5
dc.identifier.uri	https://ieeexplore.ieee.org/document/8192139
dc.identifier.uri	DOI: 10.1109/ICEE-B.2017.8192139
dc.identifier.uri	https://dspace.univ-boumerdes.dz/handle/123456789/6692
dc.language.iso	en	en_US
dc.publisher	IEEE	en_US
dc.relation.ispartofseries	2017 5th International Conference on Electrical Engineering - Boumerdes (ICEE-B);
dc.subject	EM	en_US
dc.subject	GMM	en_US
dc.subject	MFCC	en_US
dc.subject	VAD	en_US
dc.title	A new speaker verification algorithm based on identification results	en_US
dc.type	Article	en_US

Files

Now showing 1 - 2 of 2

Now showing 1 - 1 of 1