Back to Search

Adaptation to person and channel in Gaussian mixture model-based speaker verification systems Performance analysis of classical MAP-based methods

Title	Adaptation to person and channel in Gaussian mixture model-based speaker verification systems Performance analysis of classical MAP-based methods
Author	Koşunda, Serol, Yeşil, Fatih, Ayazoğlu, Yaprak, Demiroğlu, Cenk
Publication Date:	2011
Publication Place	- IEEE
Subject	Gaussian processes, Eigenvalues and eigenfunctions, Maximum likelihood estimation, Speaker recognition
Type	Document
Language	Turkish
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	978-1-4577-0462-8
Record ID	cb97dc66-2573-4f41-abdc-49dda4b88662
Library Location	Electrical & Electronics Engineering
Date	2011
Notes	Due to copyright restrictions, the access to the full text of this article is only available via subscription.
Sample Text	In this paper, performance of Gaussian mixture models (GMM) based algorithms implemented in Speech Processing Laboratory at Ozyegin University, within NIST SRE2004 and 2006 database was reported. Gaussian mixture models (GMM) is one of the most commonly used methods in text-independent speaker verification systems. In this paper, performance of the GMM approach has been measured with different parameters and settings. It has also been observed that eigenchannel-MAP and JFA methods both have increased the performance of the system against session variability which is one of the most challenging problem in text-independent speaker verification systems.
DOI	10.1109/SIU.2011.5929804

View in source Özyeğin University Özyeğin University - Ottoman library catalog search

Özyeğin University

Adaptation to person and channel in Gaussian mixture model-based speaker verification systems Performance analysis of classical MAP-based methods

Author Koşunda, Serol, Yeşil, Fatih, Ayazoğlu, Yaprak, Demiroğlu, Cenk

Publication Date 2011

Publication Place - IEEE

Subject Gaussian processes, Eigenvalues and eigenfunctions, Maximum likelihood estimation, Speaker recognition

Type Document

Language Turkish

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 978-1-4577-0462-8

Record ID cb97dc66-2573-4f41-abdc-49dda4b88662

Library Location Electrical & Electronics Engineering

Date 2011

Notes Due to copyright restrictions, the access to the full text of this article is only available via subscription.

Sample Text In this paper, performance of Gaussian mixture models (GMM) based algorithms implemented in Speech Processing Laboratory at Ozyegin University, within NIST SRE2004 and 2006 database was reported. Gaussian mixture models (GMM) is one of the most commonly used methods in text-independent speaker verification systems. In this paper, performance of the GMM approach has been measured with different parameters and settings. It has also been observed that eigenchannel-MAP and JFA methods both have increased the performance of the system against session variability which is one of the most challenging problem in text-independent speaker verification systems.

DOI 10.1109/SIU.2011.5929804