Detalle del congreso

Autores: Terissi, Lucas D.; Gómez, Juan Carlos.

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.

Tipo de reunión: Conferencia.

Tipo de trabajo: Artículo Completo.

Producción: Language Independent Speech-driven Facial Animation System.

Reunión científica: XXXIV Conferencia Latinoamericana de Informática (CLEI 2008).

Lugar: Santa Fe, Argentina.

Institución organizadora: SADIO.

Publicado: Sí

Lugar publicación: Anales de la 34º Conferencia Latinoamericana de Informática (ISBN 978-950-9770-02-7)

Mes de reunión: 12

Año: 2008.