Previs: a person-specific realistic virtual speaker

Author

Maldonado, Juvier Melenchon ; Pujol, Francesc Alias ; Sanz, Ignasi Iriondo

Author_Institution

La Salle Sch. of Eng., Ramon Llull Univ., Barcelona, Spain

Volume

1

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

461

Abstract

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.

Keywords

image representation; image sampling; image texture; speech synthesis; virtual reality; 2D realistic talking face; Previs; SAPI compliant text-to-speech engine; automated training process; emotional expressions; facial appearance model; facial gestures; head movements; image representation; lips image; mouth tracking; parameterised 2D sample based model; person-specific realistic virtual speaker; shape information; talking face personalization; talking heads; texture information; Engines; Face detection; Facial animation; Head; Human computer interaction; Image databases; Lips; Mouth; Shape; Speech synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference on

Print_ISBN

0-7803-7304-9

Type

conf

DOI

10.1109/ICME.2002.1035818

Filename

1035818