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 relationship...
In this paper we apply Bayesian networks to the problem of voicemail transcription. We use a Bayesia...
Real-life speaker verification systems are often implemented using client model adaptation methods, ...
This thesis addresses text-independent speaker verification from a machine learning point of view. W...
Cette thèse est concernée avec la modélisation statistique du signal de parole appliqué à la vérific...
Texte intégral accessible uniquement aux membres de l'Université de LorraineIn this thesis we focus ...
This paper describes the theory and implementation of Bayesian networks in the context of automatic ...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
In this paper, a probabilistic measure for reliability of speaker verification under noisy acoustic ...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
This paper describes the application of Bayesian networks to automatic speech recognition. Bayesian ...
This article provides a unifying Bayesian view on various approaches for acoustic model adaptation, ...
Abstract-In this paper, we study the general verification problem from a Bayesian viewpoint. In the ...
The aim of this paper is to reduce the effect of mismatch in recording conditions due to the transmi...
This paper explores the possibility to replace the usual thresholding decision rule of log likelihoo...
Speech signal processing has always brought a lot of attention from the communication theory communi...
In this paper we apply Bayesian networks to the problem of voicemail transcription. We use a Bayesia...
Real-life speaker verification systems are often implemented using client model adaptation methods, ...
This thesis addresses text-independent speaker verification from a machine learning point of view. W...
Cette thèse est concernée avec la modélisation statistique du signal de parole appliqué à la vérific...
Texte intégral accessible uniquement aux membres de l'Université de LorraineIn this thesis we focus ...
This paper describes the theory and implementation of Bayesian networks in the context of automatic ...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
In this paper, a probabilistic measure for reliability of speaker verification under noisy acoustic ...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
This paper describes the application of Bayesian networks to automatic speech recognition. Bayesian ...
This article provides a unifying Bayesian view on various approaches for acoustic model adaptation, ...
Abstract-In this paper, we study the general verification problem from a Bayesian viewpoint. In the ...
The aim of this paper is to reduce the effect of mismatch in recording conditions due to the transmi...
This paper explores the possibility to replace the usual thresholding decision rule of log likelihoo...
Speech signal processing has always brought a lot of attention from the communication theory communi...
In this paper we apply Bayesian networks to the problem of voicemail transcription. We use a Bayesia...
Real-life speaker verification systems are often implemented using client model adaptation methods, ...
This thesis addresses text-independent speaker verification from a machine learning point of view. W...