Audiovisual Generation of Social Attitudes from Neutral Stimuli

Adela Barbulescu 1, 2 Gérard Bailly 2 Rémi Ronfard 1 Maël Pouget 2
1 IMAGINE - Intuitive Modeling and Animation for Interactive Graphics & Narrative Environments
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 GIPSA-CRISSP - CRISSP
GIPSA-DPC - Département Parole et Cognition
Abstract : The focus of this study is the generation of expressive audiovisual speech from neutral utterances for 3D virtual actors. Taking into account the segmental and suprasegmental aspects of audiovisual speech, we propose and compare several computational frameworks for the generation of expressive speech and face animation. We notably evaluate a standard frame-based conversion approach with two other methods that postulate the existence of global prosodic audiovisual patterns that are characteristic of social attitudes. The proposed approaches are tested on a database of " Exercises in Style " [1] performed by two semi-professional actors and results are evaluated using crowdsourced perceptual tests. The first test performs a qualitative validation of the animation platform while the second is a comparative study between several expressive speech generation methods. We evaluate how the expressiveness of our audiovisual performances is perceived in comparison to resynthesized original utterances and the outputs of a purely frame-based conversion system.
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download


https://hal.inria.fr/hal-01178056
Contributor : Rémi Ronfard <>
Submitted on : Tuesday, December 22, 2015 - 9:26:02 PM
Last modification on : Monday, April 30, 2018 - 3:02:01 PM
Long-term archiving on : Sunday, April 30, 2017 - 12:09:16 AM

Files

audiovisual-generation-avsp-20...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01178056, version 1

Citation

Adela Barbulescu, Gérard Bailly, Rémi Ronfard, Maël Pouget. Audiovisual Generation of Social Attitudes from Neutral Stimuli. 1st Joint Conference on Facial Analysis, Animation and Auditory-Visual Speech Processing (FAAVSP 2015), Sep 2015, Vienne, Austria. pp.34-39. ⟨hal-01178056⟩

Share

Metrics

Record views

1052

Files downloads

423