In this PhD thesis, we aim at perfecting the phonetic transcriptions of oral readings of children learning to read, recorded in a classroom environment. These automatic transcriptions power a reading mistakes detection system used in the reading aloud exercise of the Lalilo pedagogical platform. Good accuracy is essential to provide appropriate feedback to the child, thus promoting his·her learning. A first section presents the main challenges of our task. The automatic recognition of children's speech is more difficult than adults' speech, due to its very high acoustic and prosodic variability. The scarcity of available data, especially in French, requires us to be more inventive as to correctly model its variability. Finally, frequent occ...
International audienceAutomatic recognition systems for child speech are lagging behind those dedica...
Listening comprehension is a major domain in which students are trained for when learning a foreign ...
International audienceNatural Language Processing has massively evolved during the last years and ma...
In this PhD thesis, we aim at perfecting the phonetic transcriptions of oral readings of children le...
À travers ces travaux de thèse, nous cherchons à perfectionner les transcriptions phonétiques de lec...
International audienceThe performance of automatic speech recognition systems for children is not eq...
Automatic literacy assessment of children is a complex task that normally requires carefully annotat...
Current performance of speech recognition for children is below that of the state-of-the-art for adu...
International audienceCurrent performance of automatic speech recognition (ASR) for children is belo...
Les méthodes usuelles pour la conception d'un système de reconnaissance automatique de la parole néc...
Autorisation No.1128 : De : Anne DisterEnvoyé : mercredi 30 avril 2008 16:13À : Berthille PallaudObj...
This PhD thesis was motivated by an experiment undertaken in 2007, and replicated in2008, which reve...
Summary : Listening comprehension in first-grade skilled and less-skilled comprehenders for written ...
Le développement du langage oral et des représentations phonologiques des enfants sourds est au coeu...
Usual methods to design automatic speech recognition systems require speech datasets with high quali...
International audienceAutomatic recognition systems for child speech are lagging behind those dedica...
Listening comprehension is a major domain in which students are trained for when learning a foreign ...
International audienceNatural Language Processing has massively evolved during the last years and ma...
In this PhD thesis, we aim at perfecting the phonetic transcriptions of oral readings of children le...
À travers ces travaux de thèse, nous cherchons à perfectionner les transcriptions phonétiques de lec...
International audienceThe performance of automatic speech recognition systems for children is not eq...
Automatic literacy assessment of children is a complex task that normally requires carefully annotat...
Current performance of speech recognition for children is below that of the state-of-the-art for adu...
International audienceCurrent performance of automatic speech recognition (ASR) for children is belo...
Les méthodes usuelles pour la conception d'un système de reconnaissance automatique de la parole néc...
Autorisation No.1128 : De : Anne DisterEnvoyé : mercredi 30 avril 2008 16:13À : Berthille PallaudObj...
This PhD thesis was motivated by an experiment undertaken in 2007, and replicated in2008, which reve...
Summary : Listening comprehension in first-grade skilled and less-skilled comprehenders for written ...
Le développement du langage oral et des représentations phonologiques des enfants sourds est au coeu...
Usual methods to design automatic speech recognition systems require speech datasets with high quali...
International audienceAutomatic recognition systems for child speech are lagging behind those dedica...
Listening comprehension is a major domain in which students are trained for when learning a foreign ...
International audienceNatural Language Processing has massively evolved during the last years and ma...