Dictionnaire français - anglais

sciences naturelles et appliquées - iate.europa.eu
Ce module limite le nombre de mots que le système de décodage de parole (106) peut reconnaître dans un état de contexte donné, de façon à augmenter la vitesse et la précision du processus de reconnaissance de parole.

The speech recognition manager limits the number of words that the speech decoding system (106) can recognize in a given context state in order to increase the speed and accuracy of the speech recognition process.

sciences naturelles et appliquées - wipo.int
Lvcsr rescoring with modified loss functions: a decision theoretic perspectiveThe problem of speech decoding is considered here in a Decision Theoretic framework and a modified speech decoding procedure to minimize the expected risk under a general loss function is formulated....
général - core.ac.uk - PDF: citeseerx.ist.psu.edu
A framework for fast incremental interpretation during speech decoding... The result is a single unified referential semantic probability model which brings several kinds of context to bear in speech decoding, and performs accurate recognition in real time on large domains in the absence of example in-domain training sentences....
A framework for fast incremental interpretation during speech decoding... The result is a single unified referential semantic probability model which brings several kinds of context to bear in speech decoding, and performs accurate recognition in real time on large domains in the absence of example in-domain training sentences....
A transcription-based approach to determine the difficulty of a speech recognition taskAbstract—A new parameter for estimating the difficulty of a continuous speech recognition task, called speech decoding difficulty, is presented in this work....
Softbit speech decoding with re-quantizationAbstra t | In digital mobile communication usu-ally speech decoding algorithms are closely combined with error concealment techniques to reduce the sub-jective effects of residual bit errors....
décodage de parole
sciences naturelles et appliquées - iate.europa.eu

Publications scientifiques

Etude de la performance des modèles acoustiques pour des voix de personnes âgées en vue de l'adaptation des systèmes de rap (assessment of the acoustic models performance in the ageing voice case for asr system adaptation) [in french]
... Du fait de l'évolution des caractéristiques acoustiques de la voix en fonction de l'âge, les taux d'erreurs de mots des systèmes de reconnais- sance automatique de la parole sont plus élevés lors du décodage de parole pour des personnes âgées que non-âgées....
...International audienceOur study concerns the integration of an automatic speech recognition system in a social inclusion product designed for elderly people....
général - core.ac.uk - PDF: core.ac.uk

Synonymes et termes associés français



1 milliard de traductions classées par domaine d'activité en 28 langues