Most automatic speech recognisers perform poorly when the training and testing conditions are not matched. This dissertation describes a number of algorithms that improve the noise robustness of the VINICS continuo us speech recogniser, developed at CRIN-INRIA Lorraine and based on stochastic modeling of speech trajectories.First, we give a review of recent works dealing with noisy speech recognition.Second, we propose and compare three noisy speech recognition approaches. In the first one, a noisy speech Stochastic Trajectory Model (STM) is derived from a clean speech STM and an hidden Markov model of noise. The second approach performs an STM state-based filtering of the noisy speech parametric signal, where the estimators are derived in ...
Colloque avec actes et comité de lecture. internationale.International audienceHidden Markov models ...
The role of a stochastic language model is to give the best estimation possible of the probability o...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
Performances of an automatic speech recognition system degrade when test and training conditions do ...
Performances of an automatic speech recognition system degrade when test and training conditions do ...
Colloque avec actes et comité de lecture. internationale.International audienceNoise degrades the pe...
Texte intégral accessible uniquement aux membres de l'Université de LorraineIn this thesis we focus ...
Note:This study aims to apply the Statistical Signal Mapping method to robust speech recognition. Us...
[[abstract]]© 2001 Institute of Electrical and Electronics Engineers - In this paper, an signal-to-n...
It is well known that additive noise can cause a significant decrease in performance for an automati...
Automatic speech recognition has reached high level performances but it usually fails in coping with...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
Colloque avec actes sans comité de lecture. internationale.International audienceIn real life speech...
Les performances d'un système de reconnaissance automatique de la parole se dégradent lorsque les co...
Real world applications such as hands-free dialling in cars may have to perform recognition of spoke...
Colloque avec actes et comité de lecture. internationale.International audienceHidden Markov models ...
The role of a stochastic language model is to give the best estimation possible of the probability o...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
Performances of an automatic speech recognition system degrade when test and training conditions do ...
Performances of an automatic speech recognition system degrade when test and training conditions do ...
Colloque avec actes et comité de lecture. internationale.International audienceNoise degrades the pe...
Texte intégral accessible uniquement aux membres de l'Université de LorraineIn this thesis we focus ...
Note:This study aims to apply the Statistical Signal Mapping method to robust speech recognition. Us...
[[abstract]]© 2001 Institute of Electrical and Electronics Engineers - In this paper, an signal-to-n...
It is well known that additive noise can cause a significant decrease in performance for an automati...
Automatic speech recognition has reached high level performances but it usually fails in coping with...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...
Colloque avec actes sans comité de lecture. internationale.International audienceIn real life speech...
Les performances d'un système de reconnaissance automatique de la parole se dégradent lorsque les co...
Real world applications such as hands-free dialling in cars may have to perform recognition of spoke...
Colloque avec actes et comité de lecture. internationale.International audienceHidden Markov models ...
The role of a stochastic language model is to give the best estimation possible of the probability o...
Dans cette thèse nous élaborons quatre composantes fondamentales d'un système de reconnaissance auto...