Automatic Period Segmentation of Oral French Segmentation automatique du français parlé en périodes macrosyntaxiques
Fiche du document
11 mai 2020
- handle: 10670/1.uuizyp
- hal: hal-02770725
info:eu-repo/semantics/OpenAccess
Sujets proches
Language (New words, slang, etc.) TalkingCiter ce document
Natalia Kalashnikova et al., « Segmentation automatique du français parlé en périodes macrosyntaxiques », HAL-SHS : linguistique, ID : 10670/1.uuizyp
Métriques
Partage / Export
Résumé
Natural Language Processing in oral speech segmentation is still looking for a minimal unit to analyze. In this work, we present a comparison of two automatic segmentation methods of macro-syntactic periods which allows to take into account syntactic and prosodic components of speech. We compare the performances of an existing tool Analor (Avanzi, Lacheret-Dujour, Victorri, 2008) developed for automatic segmentation of prosodic periods and of CRF models relying on syntactic and / or prosodic features. We find that Analor tends to divide speech into smaller segments and that CRF models detect larger segments rather than macro-syntactic periods. However, in general CRF models perform better results than Analor in terms of F-measure.