A CRF-Based Approach to Automatic Disfluency Detection in a French Call-Centre Corpus - Laboratoire de Phonétique et Phonologie Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

A CRF-Based Approach to Automatic Disfluency Detection in a French Call-Centre Corpus

Résumé

In this paper, we present a Conditional Random Field based approach for automatic detection of edit disfluencies in a conversational telephone corpus in French. We define disfluency patterns using both linguistic and acoustic features to perform disfluency detection. Two related tasks are considered: the first task aims at detecting the disfluent speech portion proper or reparandum, i.e. the portion to be removed if we want to improve the readability of transcribed data ; in the second task, we aim at identifying also the corrected portion or repair which can be useful in follow-up discourse and dialogue analyses or in opinion mining. For these two tasks, we present comparative results as a function of the involved type of features (acoustic and/or linguistic). Generally speaking, best results are obtained by CRF models combining both acoustic and linguistic features.
Fichier non déposé

Dates et versions

hal-01134812 , version 1 (24-03-2015)

Identifiants

  • HAL Id : hal-01134812 , version 1

Citer

Camille Dutrey, Chloé Clavel, Sophie Rosset, Ioana Vasilescu, Martine Adda-Decker. A CRF-Based Approach to Automatic Disfluency Detection in a French Call-Centre Corpus. 15th Annual Conference of the International Speech Communication Association (Interspeech'14), International Speech Communication Association (ISCA), Sep 2014, Singapour, Singapore. pp.2897-2901. ⟨hal-01134812⟩
235 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More