Automatic Period Segmentation of Oral French - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Automatic Period Segmentation of Oral French

Segmentation automatique du français parlé en périodes macrosyntaxiques

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.
Fichier principal
Vignette du fichier
609_Paper.pdf (270.49 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02770725 , version 1 (04-06-2020)

Identifiants

  • HAL Id : hal-02770725 , version 1

Citer

Natalia Kalashnikova, Loïc Grobol, Iris Eshkol-Taravella, François Delafontaine. Automatic Period Segmentation of Oral French. 12th International Conference on Language Resources and Evaluation, May 2020, Marseille, France. pp.6389-6394. ⟨hal-02770725⟩
165 Consultations
110 Téléchargements

Partager

Gmail Facebook X LinkedIn More