Generation of audio-visual prosody for expressive virtual actors

Abstract : The work presented in this thesis addresses the problem of generating audio-visual expressive performances for virtual actors. A virtual actor is represented by a 3D talking head and an audio-visual performance refers to facial expressions, head movements, gaze direction and the speech signal.While an important amount of work has been dedicated to emotions, we explore here expressive verbal behaviors that signal mental states, i.e "how speakers feel about what they say". We explore the characteristics of these so-called dramatic attitudes and the way they are encoded with speaker-specific prosodic signatures i.e. mental state-specific patterns of trajectories of audio-visual prosodic parameters.
Complete list of metadatas

Cited literature [153 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01241413
Contributor : Abes Star <>
Submitted on : Saturday, June 10, 2017 - 1:56:10 PM
Last modification on : Saturday, May 18, 2019 - 1:25:55 AM
Long-term archiving on : Wednesday, December 13, 2017 - 12:01:50 PM

File

BARBULESCU_2015_archivage.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01241413, version 2

Citation

Adela Barbulescu. Generation of audio-visual prosody for expressive virtual actors. Graphics [cs.GR]. Université Grenoble Alpes, 2015. English. ⟨NNT : 2015GREAM071⟩. ⟨tel-01241413v2⟩

Share

Metrics

Record views

732

Files downloads

434