Current automatic speech recognition (ASR) systems are based on language models (LM) which gather word sequence probabilities (n-gram probabilities) and assist the system in discriminating utterances with the highest likelihood. In practice, these ngram probabilities are estimated once and for all on large multitopic corpora based on a fixed, though large, general-purpose vocabulary. Hence, current systems suffer from a lack of specificity when dealing with topic-specific spoken documents. To circumvent this problem, we propose to modify the LM and the vocabulary through a new unsupervised topic-based adaptation scheme. Based on the sole automatic transcription of a thematically consistent broadcast segment, the process consists in automati...
International audienceThis paper discusses the adaptation of speech recognition vocabularies for aut...
Cette thèse s’inscrit dans le cadre d’une étude sur le potentiel de la transcription automatique pou...
International audienceOut-of-vocabulary (OOV) words can pose a particular problem for automatic spee...
Current automatic speech recognition (ASR) systems are based on language models (LM) which gather wo...
Dans cette thèse, nous proposons un processus d'adaptation thématique non supervisée qui vise à spéc...
A way to improve outputs produced by automatic speech recognition (ASR) systems is to integrate addi...
Texte intégral accessible uniquement aux membres de l'Université de LorraineOne way to improve perfo...
This thesis is part of a study that explores automatic transcription potential for the instrumentati...
International audienceWhereas topic-based adaptation of language models (LM) claims to increase the ...
In statistical language modelling researches, there is a lack of huge text corpora, especially for s...
Language models used in current automatic speech recognition systems are trained on general-purpose ...
International audienceThis paper discusses the adaptation of vocabularies for automatic speech recog...
Modern automatic speech recognition (ASR) systems are speaker independent and designed to recognize ...
Automatic speech recognition (ASR) systems currently reach enough performance to be integrated in va...
The three pillars of an automatic speech recognition system are the lexicon, the languagemodel and t...
International audienceThis paper discusses the adaptation of speech recognition vocabularies for aut...
Cette thèse s’inscrit dans le cadre d’une étude sur le potentiel de la transcription automatique pou...
International audienceOut-of-vocabulary (OOV) words can pose a particular problem for automatic spee...
Current automatic speech recognition (ASR) systems are based on language models (LM) which gather wo...
Dans cette thèse, nous proposons un processus d'adaptation thématique non supervisée qui vise à spéc...
A way to improve outputs produced by automatic speech recognition (ASR) systems is to integrate addi...
Texte intégral accessible uniquement aux membres de l'Université de LorraineOne way to improve perfo...
This thesis is part of a study that explores automatic transcription potential for the instrumentati...
International audienceWhereas topic-based adaptation of language models (LM) claims to increase the ...
In statistical language modelling researches, there is a lack of huge text corpora, especially for s...
Language models used in current automatic speech recognition systems are trained on general-purpose ...
International audienceThis paper discusses the adaptation of vocabularies for automatic speech recog...
Modern automatic speech recognition (ASR) systems are speaker independent and designed to recognize ...
Automatic speech recognition (ASR) systems currently reach enough performance to be integrated in va...
The three pillars of an automatic speech recognition system are the lexicon, the languagemodel and t...
International audienceThis paper discusses the adaptation of speech recognition vocabularies for aut...
Cette thèse s’inscrit dans le cadre d’une étude sur le potentiel de la transcription automatique pou...
International audienceOut-of-vocabulary (OOV) words can pose a particular problem for automatic spee...