HMM inversion with full and diagonal covariance matrices for audio-to-visual conversion

LUCAS D. TERISSI, JUAN C. GÓMEZ

Porto, Portugal

Conferencia; International Conference on Signal Processing and Multimedia Applications (SIGMAP 2008); 2008

INSTICC

A speech driven MPEG-4 compliant facial animation system is proposed in this paper. The main feature of the system is the audio-to-visual conversion based on the inversion of an Audio-Visual Hidden Markov Model. The Hidden Markov Model Inversion algorithm is derived for the general case of considering full covariance matrices for the audio-visual observations. A performance comparison with the more common case of considering diagonal covariance matrices is carried out. Experimental results show that the use of full covariance matrices is preferable since it leads to an accurate estimation of the visual parameters, yielding the same performance as in the case of using diagonal covariance matrices, but with a less complex model.