Fiche du document
21 avril 2023
- handle: 10670/1.lszr1n
- isbn: 978-83-232-4176-8
- hal: hal-04081282
http://creativecommons.org/licenses/by-nc/ , info:eu-repo/semantics/OpenAccess
Mots-clés
cued speech corpus annotationSujets proches
TalkingCiter ce document
Brigitte Bigi, « An analysis of produced versus predicted French Cued Speech keys », HAL-SHS : linguistique, ID : 10670/1.lszr1n
Métriques
Partage / Export
Résumé
Cued Speech is a communication system developed for deaf people to complement speechreading at the phonetic level with hands. This visual communication mode uses handshapes in different placements near the face in combination with the mouth movements of speech to make the phonemes of spoken language look different from each other. This paper presents an analysis on produced cues in 5 topics of CLeLfPC, a large corpus of read speech in French with Cued Speech. A phonemes-to-cues automatic system is proposed in order to predict the cue to be produced while speaking. This system is part of SPPAS-the automatic annotation an analysis of speech, an open source software tool. The predicted keys of the automatic system are compared to the produced keys of cuers. The number of inserted, deleted and substituted keys are analyzed. We observed that most of the differences between predicted and produced keys comes from 3 common position's substitutions by some of the cuers.