Training a Talking Head

Authors:
Michael M. Cohen;Dominic W. Massaro;Rashid Clark
Affiliations:
University of California at Santa Cruz;University of California at Santa Cruz;University of California at Santa Cruz
Venue:
ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces
Year:
2002

Citing 1
Cited 4

Shape transformation for polyhedral objects

SIGGRAPH '92 Proceedings of the 19th annual conference on Computer graphics and interactive techniques

Towards perceptually realistic talking heads: models, methods and McGurk

APGV '04 Proceedings of the 1st Symposium on Applied perception in graphics and visualization
A framework for evaluating multimodal integration by humans and a role for embodied conversational agents

Proceedings of the 6th international conference on Multimodal interfaces
Toward Perceptually Realistic Talking Heads: Models, Methods, and McGurk

ACM Transactions on Applied Perception (TAP)
Model-based synthesis of visual speech movements from 3D video

SIGGRAPH '09: Posters

Quantified Score

Hi-index	0.00

Visualization

Abstract

A Cyberware laser scan of DWM was made, Baldi's generic morphology was mapped into the form of DWM, this head was trained on real data recorded with Optotrak LED markers, and the quality of its speech was evaluated. Participants were asked to recognize auditory sentences presented alone in noise, aligned with the newly trained synthetic textured mapped target face, or the original natural face. There was a significant advantage when the noisy auditory sentence was paired with either head, with the synthetic textured mapped target face giving as much of an improvement as the original recordings of the natural face.