Loading...
Please wait, while we are loading the content...
Similar Documents
Combinaison de reconnaissance de la parole, reconnaissance des émotions et tête parlante codeuse en LPC pour les personnes sourdes et malentendantes
| Content Provider | Semantic Scholar |
|---|---|
| Author | Daassi-Gnaba, Hela Zbakh, Mohammed Krahe, Jaime López |
| Copyright Year | 2009 |
| Abstract | We present here an original approach based on the combination of speech recognition, emotion recognition and a talking head generating CS (Cued Speech). This approach completes a previous research that provided lip readers and, especially deaf and impaired hearing people with an artificial talking head controlled by automatic speech recognition (Labiao, 2005). The talking head can be lip read and, if needed, can produce CS (Cornett, 1967 ; Krahe et al, 2007). However, the system users require not only the linguistic content speech but also its emotional part. Hence, the talking head can be improved by the introduction of an advanced technique for the recognition and synthesis of the speaker's emotional state. This approach belongs to the speech analysis methods, in order to create a multimodal interface between speaker and listener (hearing impaired). The aim of this interface is to improve speech recognition. MOTS-CLES : Personnes sourdes, personnes malentendantes, descripteurs acoustiques, reconnaissance de la parole, reconnaissance des emotions, tete parlante, Langage Parle Complete. |
| Starting Page | 239 |
| Ending Page | 253 |
| Page Count | 15 |
| File Format | PDF HTM / HTML |
| DOI | 10.3166/sth.3.239-253 |
| Volume Number | 3 |
| Alternate Webpage(s) | http://www2.univ-paris8.fr/ingenierie-cognition/master-handi/recherche/IFRATH%20STH%20papier%20Hela.pdf |
| Alternate Webpage(s) | https://doi.org/10.3166/sth.3.239-253 |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
