PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Multimedia Mapping using Continuous State Space Models
Tue Lehn-Schiøler
In: MMSP, 29 Sep - 1 Oct, Siena, Italy.

Abstract

In this paper a system that transforms speech waveforms to animated faces are proposed. The system relies on a state space model to perform the mapping. To create a photo realistic image an Active Appearance Model is used. The main contribution of the paper is to compare a Kalman filter and a Hidden Markov Model approach to the mapping. It is shown that even though the HMM can get a higher test likelihood the Kalman filter is easier to train and the animation quality is better for the Kalman filter.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Multimodal Integration
ID Code:231
Deposited By:Tue Lehn-Schiøler
Deposited On:23 November 2004