Theme Identification in Telephone Service Conversations using Quaternions of Speech Features - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Theme Identification in Telephone Service Conversations using Quaternions of Speech Features

Mohamed Morchid
Georges Linarès
Marc El Bèze
  • Fonction : Auteur
  • PersonId : 949557

Résumé

The paper introduces new features for describing possible focus variation in a human/human conversation. The application considered is a real-life telephone customer care service. The purpose is to hypothesize the dominant theme of conversations between a casual customer calling. Conversations are processed by an automatic speech recognition system that provides hypotheses used for extracting word frequency. Features are extracted in different, broadly defined and partially overlapped, time segments. Combinations of each feature in different segments are represented in a quaternion algebra framework. The advantage of the proposed approach is made evident by the statistically significant improvements in theme classification accuracy .
Fichier non déposé

Dates et versions

hal-01339930 , version 1 (30-06-2016)

Identifiants

  • HAL Id : hal-01339930 , version 1

Citer

Mohamed Morchid, Georges Linarès, Marc El Bèze, Renato de Mori. Theme Identification in Telephone Service Conversations using Quaternions of Speech Features. Interspeech 2013, Aug 2013, Lyon, France. ⟨hal-01339930⟩

Collections

UNIV-AVIGNON LIA
86 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More