Skip to Main content Skip to Navigation
Theses

Dynamic Bayesian Networks for Speaker Verification

Abstract : This thesis is concerned with the statistical modeling of speech signal applied to Speaker Verification (SV) using Bayesian Networks (BNs). The main idea of this work is to use BNs as a mathematical tool to model pertinent speech features keeping its relations. It combines theoretical and experimental work. The difference between systems and humans performance in SV is the quantity of information and the relationships between the sources of information used to make decisions. A single statistical framework that keeps the conditional dependence and independence relations between those variables is difficult to attain. Therefore, the use of BNs as a tool for modeling the available information and their independence and dependence relationships is proposed. The first part of this work reviews the main modules of a SV system, the possible sources of information as well as the basic concepts of graphical models. The second part deals with Modeling. A new approach to the problems associated with the SV systems is proposed. The problem of inference and learning (parameters and structure) in BNs are presented. In order to obtain an adapted structure the relations of conditional independence among the variables are learned directly from the data. These relations are then used in order to build an adapted BN. In particular, a new model adaptation technique for BN has been proposed. This adaptation is based on a measure between Conditional Probability Distributions for discrete variables and on Regression Matrix for continuous variables used to model the relationships. In a large database for the SV task, the results have confirmed the potential of use the BNs approach.
Complete list of metadatas

https://pastel.archives-ouvertes.fr/tel-00011440
Contributor : Eduardo Sanchez-Soto <>
Submitted on : Friday, January 20, 2006 - 7:00:07 PM
Last modification on : Friday, July 31, 2020 - 10:44:07 AM
Long-term archiving on: : Saturday, April 3, 2010 - 9:38:00 PM

Identifiers

  • HAL Id : tel-00011440, version 1

Collections

Citation

Eduardo Sanchez-Soto. Dynamic Bayesian Networks for Speaker Verification. Signal and Image processing. Télécom ParisTech, 2005. English. ⟨tel-00011440⟩

Share

Metrics

Record views

358

Files downloads

825