Cette thèse se focalise sur la reconnaissance automatique de la parole (RAP) robuste au bruit. Elle comporte deux parties. Premièrement, nous nous focalisons sur une meilleure prise en compte des incertitudes pour améliorer la performance de RAP en environnement bruité. Deuxièmement, nous présentons une méthode pour accélérer l'apprentissage d'un réseau de neurones en utilisant une fonction auxiliaire. Dans la première partie, une technique de rehaussement multicanal est appliquée à la parole bruitée en entrée. La distribution a posteriori de la parole propre sous-jacente est alors estimée et représentée par sa moyenne et sa matrice de covariance, ou incertitude. Nous montrons comment propager la matrice de covariance diagonale de l'incerti...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
Note:This study aims to apply the Statistical Signal Mapping method to robust speech recognition. Us...
We introduce a new paradigm for Robust Automatic Speech Recognition that directly incorporates infor...
This thesis focuses on noise robust automatic speech recognition (ASR). It includes twoparts. First,...
International audienceWe consider the framework of uncertainty propagation for automatic speech reco...
International audienceUncertainty decoding has been successfully used for speech recognition in high...
International audienceWe consider the problem of robust automatic speech recognition (ASR) in noisy ...
The term uncertainty decoding has been phrased for a class of robustness enhancing algorithms in aut...
International audienceWe consider the problem of uncertainty estimation for noise-robust ASR. Existi...
International audienceIn order to improve the ASR performance in noisy environments , distorted spee...
Most automatic speech recognisers perform poorly when the training and testing conditions are not ma...
International audienceThe uncertainty decoding framework is known to improve deep neural network (DN...
International audienceAutomatic speech recognition (ASR) in noisy environments remains a challenging...
In this paper we develop different mathematical models in the framework of the multi-stream paradigm...
We consider the problem of Gaussian mixture model (GMM)-based classification of noisy data, where th...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
Note:This study aims to apply the Statistical Signal Mapping method to robust speech recognition. Us...
We introduce a new paradigm for Robust Automatic Speech Recognition that directly incorporates infor...
This thesis focuses on noise robust automatic speech recognition (ASR). It includes twoparts. First,...
International audienceWe consider the framework of uncertainty propagation for automatic speech reco...
International audienceUncertainty decoding has been successfully used for speech recognition in high...
International audienceWe consider the problem of robust automatic speech recognition (ASR) in noisy ...
The term uncertainty decoding has been phrased for a class of robustness enhancing algorithms in aut...
International audienceWe consider the problem of uncertainty estimation for noise-robust ASR. Existi...
International audienceIn order to improve the ASR performance in noisy environments , distorted spee...
Most automatic speech recognisers perform poorly when the training and testing conditions are not ma...
International audienceThe uncertainty decoding framework is known to improve deep neural network (DN...
International audienceAutomatic speech recognition (ASR) in noisy environments remains a challenging...
In this paper we develop different mathematical models in the framework of the multi-stream paradigm...
We consider the problem of Gaussian mixture model (GMM)-based classification of noisy data, where th...
Revised version including a bugfix in the computation of the Wiener uncertainty estimator and in the...
Note:This study aims to apply the Statistical Signal Mapping method to robust speech recognition. Us...
We introduce a new paradigm for Robust Automatic Speech Recognition that directly incorporates infor...