Publikationsansicht

Multimedia Mapping using Continuous State Space Models (2004)

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.

Details der Publikation
Download http://eprints.pascal-network.org/archive/00000231/
Archiv PASCAL EPrints (United Kingdom)
Keywords Multimodal Integration
Typ Conference or Workshop Item, PeerReviewed
Verknüpfungen http://eprints.pascal-network.org/archive/00000231/01/mmsp.pdf

Literaturangaben in der Publikation (3)
An HMM-Based Speech-to-Video Synthesizer (2002)
Parameter Estimation for Linear Dynamical Systems (1996)
Mapping from Speech to Images Using Continuous State Space Models (2004)