Previs: A person-specific realistic virtual speaker

Juvier Melenchón Maldonado, Fruncesc Alías Pujol, Ignusi Iriondo Sanz

Producción científica: Capítulo del libroContribución a congreso/conferenciarevisión exhaustiva

1 Cita (Scopus)

Resumen

This paper describes a 2D realistic talking face. The facial appearance model is constructed with a parameterised 2D sample based model. This representation supports moderated head movements, facial gestures and emotional expressions. Two main contributions for talking heads applications are proposed. First, the image of the lips is synthesized by means of shape and texture information. Secondly, a nearly automated training process makes the talking face personalization easier, due to the use of mouth tracking. Additionally, lips are synchronized in real time with speech that is generated using a SAPI compliant text-to-speech engine.

Idioma originalInglés
Título de la publicación alojadaProceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas461-464
Número de páginas4
ISBN (versión digital)0780373049
DOI
EstadoPublicada - 2002
Evento2002 IEEE International Conference on Multimedia and Expo, ICME 2002 - Lausanne, Suiza
Duración: 26 ago 200229 ago 2002

Serie de la publicación

NombreProceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002
Volumen1

Conferencia

Conferencia2002 IEEE International Conference on Multimedia and Expo, ICME 2002
País/TerritorioSuiza
CiudadLausanne
Período26/08/0229/08/02

Huella

Profundice en los temas de investigación de 'Previs: A person-specific realistic virtual speaker'. En conjunto forman una huella única.

Citar esto