L. M. Arslan and D. Talkin, 1999, "Codebook Based Face Point Trajectory Synthesis Algorithm using Speech Input," in Speech Communication 27, pp. 81-93. Home/Search Document Details and Download
Summary Related Articles |
This paper is cited in the following contexts:
Speech Driven Facial Animation - Kakumanu, Gutierrez-Osuna, Esposito, .. (2001) (1 citation) (Correct)
.... from text (orthographic or phonetic) onto visemes by means of vector quantization [11, 12] or a rule based system [13, 14] Facial animation driven by speech can be approached in a similar fashion by deriving the phoneme sequence directly from the speech signal, as done in speech recognition [15, 16, 17]. However, mapping from acoustic frames to phonetic units and then to animation frames involves introducing additional uncertainty that often slights prosodic variables (e.g. pitch, duration or amplitude) It is more appealing, therefore, to construct a direct mapping from speech acoustics (e.g. ....
L. M. Arslan and D. Talkin, 1999, "Codebook Based Face Point Trajectory Synthesis Algorithm using Speech Input," in Speech Communication 27, pp. 81-93.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC