Abstract
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.
| Original language | English |
|---|---|
| Title of host publication | IEEE 6th workshop on Multimedia Signal Processing Proceedings |
| Publication date | 2004 |
| Pages | 51-54 |
| Publication status | Published - 2004 |
| Event | 2004 IEEE 6th Workshop on Multimedia Signal Processing - Siena, Italy Duration: 29 Sept 2004 → 1 Oct 2004 Conference number: 6 https://ieeexplore.ieee.org/document/1436389 |
Conference
| Conference | 2004 IEEE 6th Workshop on Multimedia Signal Processing |
|---|---|
| Number | 6 |
| Country/Territory | Italy |
| City | Siena |
| Period | 29/09/2004 → 01/10/2004 |
| Internet address |
Fingerprint
Dive into the research topics of 'Multimedia Mapping using Continuous State Space Models'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver