Name
Abstract | ||
|---|---|---|
Two dimensional (2D) shape and appearance models are applied to the problem of creating a near-videorealistic talking head. A speech corpus of a talker uttering a set of phonetically balanced training sentences is analysed using a generative model of the human face. Segments of original parameter trajectories corresponding to the synthesis unit (e.g. triphone), are extracted from a codebook, then normalised, blended, concatenated and smoothed be- fore being applied to the model to give natural, realistic animations of novel utterances. The system provides a 2D image sequence corresponding to the face of a talker. It is also used to animate the face of a 3D avatar by dis- placing the mesh according to movements of points in the shape model and dynamically texturing the face polygons using the appearance model. |
Year | Venue | Field |
|---|---|---|
2003 | BMVC | Speech corpus,Computer science,Concatenation,Artificial intelligence,Avatar,Computer vision,Speech synthesis,Polygon,Pattern recognition,Active appearance model,Speech recognition,Generative model,Codebook |
DocType | Citations | PageRank |
Conference | 5 | 0.50 |
References | Authors | |
12 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Barry-John Theobald | 1 | 332 | 25.39 |
| J. Andrew Bangham | 2 | 5 | 0.50 |
| Iain Matthews | 3 | 408 | 22.16 |
| John R. W. Glauert | 4 | 77 | 9.24 |
| Gavin Cawley | 5 | 77 | 6.38 |