Conference paper
Multimedia Mapping using Continuous State Space Models
In this paper a system that transforms speech waveforms to animated faces are proposed. The system relies on continuous state space models to perform the mapping, this makes it possible to ensure video with no sudden jumps and allows continuous control of the parameters in 'face space'. Simulations are performed on recordings of 3-5 sec. video sequences with sentences from the Timit database.
The model is able to construct an image sequence from an unknown noisy speech sequence fairly well even though the number of training examples are limited.
| Language: | English |
|---|---|
| Year: | 2004 |
| Pages: | 51-54 |
| Proceedings: | 2004 IEEE 6th Workshop on Multimedia Signal Processing |
| ISBN: | 0780385780 and 9780780385788 |
| Types: | Conference paper |
| DOI: | 10.1109/MMSP.2004.1436413 |
Data mining Facial animation Hidden Markov models Kalman filter Kalman filters Mathematical model Motion pictures Mouth Neural networks Speech State-space methods Training data active appearance model animation quality computer animation continuous state space model feature extraction hidden Markov model approach hidden Markov models multimedia communication multimedia mapping speech waveform state-space methods transforms
