RÉSUMÉ La construction de corpus de parole est une étape cruciale pour tout système de synthèse de la parole à partir du texte. L’usage de modèles statistiques nécessite aujourd’hui l’utilisation de corpus de très grande taille qui doivent être enregistrés, transcrits, annotés et segmentés afin d’être exploitables. La variété des corpus nécessaire aux applications actuelles (contenu, style, etc...

This paper deals with spontaneous speech, considering first its specificities, and then its transcription – both diachronically and synchronically. The paper continues by listing the main problems spontaneous speech causes to automatic speech recognition systems, which were identified through several experiments. It ends by suggesting some optimizations to help solve these problems. MOTS-CLÉS :...

This article describes a novel approach to linguistic field research consisting in exploiting the self-regulation of a market for collecting data on language use. The market is conceived as an output-agreement game with a purpose called Borsa Parole. The agreement can be traded with by the players what makes it adjustable. Borsa Parole has been conceived and is deployed for a linguistic study o...

This article describes a novel approach to linguistic field research consisting in exploiting the self-regulation of a market for collecting data on language use. The market is conceived as an output-agreement game with a purpose called Borsa Parole. The agreement can be traded with by the players what makes it adjustable. Borsa Parole has been conceived and is deployed for a linguistic study o...

The success of future syste ms for computer assisted foreign language learning relies on providing the learner personalized diagnosis and relevant corrections of its pronunciations. After a presentation of the problem of reliable automatic prosodic feedbacks in language learning, we present our work related to the processing of some errors stemming from the learner and from the system itself. T...

RÉSUMÉ. Le traitement automatique de la parole peut concrètement contribuer à éclairer de nombreuses questions concernant la variabilité phonémique à l’oral. L’exploitation de grandes masses de données permet ainsi de dégager de grandes tendances, dont une interprétation plus fine repose ensuite à la fois sur un éclairage linguistique et sur un certain nombre de précautions méthodologiques. Nou...

The ability of a group of Canadian federal parole officers to detect deception was investigated over the course of 2 days of lie detection training. On the first day of training, 32 officers judged the honesty of 12 (6 true, 6 fabricated) videotaped speakers describing personal experiences, half of which were judged before and half judged after training. On the second day, 5 weeks later, 20 of ...

Research Summary: This study analyzed data on 7,306 offenders placed in 1 of 53 community-based residential programs as part of their parole, postrelease control, or probation. Offenders who successfully completed residential programming were compared with a group of offenders (n = 5801) under parole/post-release control who were not placed in residential programming. Analyses of program effect...