Authors: Terissi, Lucas D.; Gómez, Juan Carlos.
Title: Language Independent Speech-driven Facial Animation System.
Resumen: In this paper, a speech-driven MPEG-4 compliant facial animation system is proposed. The system is based on the inversion of a joint Audio-Visual Hidden Markov Model to estimate the visual information from speech data. The inversion algorithm is derived for the general case of considering full covariance matrices for the audio-visual observations. The proposed speech-driven facial animation system operates at a subphonemic level, with the advantage of being adaptable to any language. The experiments are carried out using audio-visual databases compiled by the authors.
Meeting type: Conferencia.
Type of job: Artículo Completo.
Production: Language Independent Speech-driven Facial Animation System.
Scientific meeting: XXXIV Conferencia Latinoamericana de Informática (CLEI 2008).
Meeting place: Santa Fe, Argentina.
Organizing Institution: SADIO.
It's published?: Yes
Publication place: Anales de la 34º Conferencia Latinoamericana de Informática (ISBN 978-950-9770-02-7)
Meeting month: 12