Method and system for aligning natural and synthetic video...

Details Method and system for aligning natural and synthetic video... Method and system for aligning natural and synthetic video...

G - Physics

06

K

G06K 9/78 (2006.01) G06T 1/00 (2006.01) G10L 13/04 (2006.01) G10L 15/24 (2006.01) G10L 21/06 (2006.01) H04N 7/26 (2006.01) H04N 7/50 (2006.01)

Patent

CA 2244624

According to MPEG-4's TTS architecture, facial animation can be driven by two streams simultaneously - text, and Facial Animation Parameters. In this architecture, text input is sent to a Text-To-Speech converter at a decoder that drives the mouth shapes of the face. Facial Animation Parameters are sent from an encoder to the face over the communication channel. The present invention includes codes(known as bookmarks) in the text string transmitted to the Text-to-Speech converter, which bookmarks are placed between words as well as inside them. According to the present invention, the bookmarks carry an encoder time stamp. Due to the nature of text-to-speech conversion, the encoder time stamp does not relate to real-world time, and should be interpreted as a counter. In addition, the Facial Animation Parameter stream carries the same encoder time stamp found in the bookmark of the text. The system of the present invention reads the bookmark and provides the encoder time stamp as well as a real-time time stamp to the facial animation system. Finally, the facial animation system associates the correct facial animation parameter with the real-time time stamp using the encoder time stamp of the bookmark as a reference.

L'architecture MPEG-4 TTS permet la commande d'animation faciale par deux trains simultanés - paramètres d'animation faciale et texte. Dans cette architecture, le texte d'entrée est transmis à un convertisseur texte-parole d'un décodeur qui commande les formes de la bouche du visage. Les paramètres d'animation faciale sont transmis d'un codeur au visage sur le canal de communication. La présente invention comprend des codes appelés signets, inclus dans la chaîne textuelle transmise au convertisseur texte-parole, signets qui sont placés entre les mots et à l'intérieur des mots. Suivant la présente invention, les signets véhiculent un horodateur codeur. Étant donné la nature de la conversion texte-parole, l'horodateur codeur n'est pas lié au temps du monde réel, et devrait être considéré comme un compteur. En outre, le train de paramètres d'animation faciale véhicule le même horodateur codeur que le signet du texte. Le système de la présente invention lit le signet et transmet l'horodateur codeur ainsi que l'horodateur temps réel au système d'animation faciale. Enfin, le système d'animation faciale associe le paramètre d'animation faciale pertinent à l'horodateur temps réel en utilisant comme référence l'horodateur codeur du signet.

Affiliated with

Also associated with

Rating

Method and system for aligning natural and synthetic video... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and system for aligning natural and synthetic video..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for aligning natural and synthetic video... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFCA-PAI-O-1785807