Skip to Main content Skip to Navigation
Theses

Reconnaissance automatique des dimensions affectives dans l'interaction orale homme-machine pour des personnes dépendantes

Abstract : Most of the affective states recognition systems are trained on artificial data, without any realistic context. Moreover the evaluations are done with pre-recorded data of the same quality. This thesis seeks to tackle the various challenges resulting from the confrontation of these systems with real situations and users.In order to obtain close-to-reality spontaneous emotional data, a data-collection system simulating a natural interaction was developed. It uses an expressive virtual character to conduct the interaction. Two emotional corpora where gathered with this system, with almost 80 patients from medical centers of the region of Montpellier, France, participating in. This work was carried out as part of the French ANR ARMEN collaborative project.This data was used to explore approaches to solve the problem of performance generalization for emotion detection systems. Most of the work in this part deals with cross-corpus strategies and automatic selection of the best features. An hybrid algorithm combining floating selection techniques with similarity measures and multi-scale heuristics was proposed and used in the frame of the InterSpeech 2012 Emotino Challenge. The results and insights gained with the help of this algorithm suggest ways of distinguishing between emotional corpora using their most relevant features.A prototype of the complete dialog system, including the emotion detection module and the virtual agent was also implemented.
Document type :
Theses
Complete list of metadatas

Cited literature [266 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00923201
Contributor : Abes Star :  Contact
Submitted on : Thursday, January 2, 2014 - 2:28:42 AM
Last modification on : Monday, December 14, 2020 - 9:52:54 AM
Long-term archiving on: : Saturday, April 8, 2017 - 9:29:04 AM

File

VD2_CHASTAGNOL_CLEMENT_0410201...
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-00923201, version 1

Collections

Citation

Clément Chastagnol. Reconnaissance automatique des dimensions affectives dans l'interaction orale homme-machine pour des personnes dépendantes. Autre [cs.OH]. Université Paris Sud - Paris XI, 2013. Français. ⟨NNT : 2013PA112190⟩. ⟨tel-00923201⟩

Share

Metrics

Record views

674

Files downloads

2065