Graphical models for text-independent speaker verification

Authors:
Eduardo Sánchez-Soto;Marc Sigelle;Gérard Chollet
Affiliations:
Département de Traitement du Signal et des Images, CNRS UMR LTCI, École Nationale Supérieure des Télécommunications, Paris Cedex 13, France;Département de Traitement du Signal et des Images, CNRS UMR LTCI, École Nationale Supérieure des Télécommunications, Paris Cedex 13, France;Département de Traitement du Signal et des Images, CNRS UMR LTCI, École Nationale Supérieure des Télécommunications, Paris Cedex 13, France
Venue:
Nonlinear Speech Modeling and Applications
Year:
2005

Citing 3
Cited 1

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
A Bayesian Method for the Induction of Probabilistic Networks from Data

Machine Learning
A tutorial on learning with Bayesian networks

Learning in graphical models

Speaker Classification Concepts: Past, Present and Future

Speaker Classification I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Our approach in text independent Speaker Verification (SV) proposes to integrate different aspects of the speech signal which convey information about the speaker's identity using Graphical Models (GM). Prosodic, spectral and source information obtained from the residue of linear prediction analysis are modeled in a probabilistic framework with a system based on Bayesian Networks (BN). The structure, or conditional independencies between the variables, is learned directly from the data using two different algorithms. In particular, the interpretation and comparation of the structures is presented. Some experiments conducted on the NIST 2003 one speaker text-independent data base have been conducted to demonstrate the feasibility of this approach.