Previs: a person-specific realistic virtual speaker

J.M. Maldonado1, F.A. Pujol1, I.I. Sanz1
1La Salle School of Engineering, Ramon Llull University, Barcelona, Spain

Tóm tắt

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.

Từ khóa

#Head #Speech synthesis #Human computer interaction #Facial animation #Lips #Shape #Mouth #Image databases #Face detection #Engines

Tài liệu tham khảo

jolliffe, 1986, Principal Component Analysis, 10.1007/978-1-4757-1904-8 ekman, 1978, Facial Action Cosing System maestri, 1996, Digital Character Animation 10.1145/133994.134003 noh, 2000, Talking faces, IEEE International Conference on Multimedia and Expo (II), 627 10.1109/79.924886 10.1145/218380.218407 ostermann, 1997, Animated talking head with personalized 3d head model, Proc Workshop Multimedia Signal Processing, 274 kurakate, 1997, Facial animation from 3d kinematics, ASJ de la torre, 2000, Eigenfiltering for flexible eigentracking, 15th International Conference on Pattern Recognition (ICPR), 10.1109/ICPR.2000.903739 cootes, 1998, Active appearance models, 5th ECCV guaus, 2000, Diphone based unit selection for catalan tts synthesis, TSD 0 0 10.1109/RATFG.2001.938907 10.1109/CA.1998.681914 beskow, 0, The teleface project multi-modal speech-communication for the hearing impaired, Proc Eurospeech 97 10.1109/34.216726 alan, 2001, A Facial Model and Animation Techniques for Animated Speech pelachaud, 2001, Modelling an italian head, Audio- Visual Speech Processing 10.1145/258734.258880 10.1109/ICASSP.1998.679713 10.1109/AFGR.1996.557252 10.1145/800193.569955 10.1038/264746a0