The following information was submitted:
Transactions: SIMULATION AND MODELLING
Transactions ID Number: 10-135
Full Name: Mario Malcangi
Position: Professor
Age: ON
Sex: Male
Address: Via Comelico 39
Country: ITALY
Tel:
Tel prefix:
Fax:
E-mail address: malcangi@dico.unimi.it
Other E-mails: m.malcangi@alice.it
Title of the Paper: Text-driven avatars based on artificial neural networks and fuzzy logic
Authors as they appear in the Paper: Malcangi Mario
Email addresses of all the authors: malcangi@dico.unimi.it
Number of paper pages: 10
Abstract: We discuss a new approach for driving avatars using synthetic speech generated from pure text. Lip and face muscles are controlled by the information embedded in the utterance and its re-lated expressiveness. Rule-based, text-to-speech synthesis is used to generate phonetic and expression transcriptions of the text to be uttered by the avatar. Two artificial neural networks, one for text-to-phone transcription and the other for phone-to-viseme mapping have been trained from phonetic transcription data. Two fuzzy-logic engines were tuned for smoothed control of lip and face movement. Simulations have been run to test neural-fuzzy controls using a parametric speech synthesizer to generate voices and a face synthesizer to generate facial movement. Experimental results show that soft computing affords a good solution for the smoothed control of avatars during the expressive utterance of text.
Keywords: Speech-driven avatar, phone-to-viseme conversion, text-to-speech synthesis, artificial neural network, fuzzy logic.
EXTENSION of the file: .doc
Special (Invited) Session: Soft-computing methods for text-to-speech driven avatars
Organizer of the Session: 619-225
How Did you learn about congress:
IP ADDRESS: 159.149.138.11
