Animating Virtual Speakers or Singers from Audio: Lip-Synching Facial Animation

Special Issue Details

Lip synchronization (lip-synch) is the term used to describe matching lip movements to a prerecorded speaking or singing voice. We focus here on technologies that are able to compute automatically the facial movements of animated characters given prerecorded audio.

http://www.hindawi.com/journals/asmp/si/lsfa.html

Call for Papers

Animating Virtual Speakers or Singers from Audio: Lip-Synching Facial Animation

Call for Papers

Lip synchronization (lip-synch) is the term used to describe matching lip movements to a prerecorded speaking or singing voice. This often is used in the production of films, cartoons, television programs, and computer games.We focus here on technologies that are able to compute automatically the facial movements of animated characters given prerecorded audio. Automating the lip-synch process, generally termed visual speech synthesis, has potential for use in a wide range of applications: from desktop agents on personal computers to language translation tools to providing a means for generating and displaying stimuli in speech perception experiments.

A visual speech synthesizer comprises at least three modules: a control model that computes articulatory trajectories from the input signal, a shape model that animates the facial geometry from computed trajectories, and an appearance model for rendering the animation by varying the colors of pixels. There are numerous solutions proposed in the literature for each of these modules. Control models exploit either direct signal-to-articulation mappings or more complex trajectory formation systems that utilize a phonetic segmentation of the acoustic signal. Shape models vary from ad hoc parametric deformations of a 2D mesh to sophisticated 3D biomechanical models. Appearance models exploit morphing of natural images, texture blending, or more sophisticated texture models.

The aim of this Special Issue is to provide a detailed description of state-of-the-art systems and to identify new techniques that have recently emerged from both the audiovisual speech and computer graphics research communities.

In particular, we solicit original, previously unpublished research on:

Audiovisual synthesis from text
Facial animation from audio
Trajectory formation systems
Evaluation methods for audiovisual synthesis
Perception of audiovisual asynchrony in speech and music
Control of speech and facial expressions

This Special Issue follows the first visual speech synthesis challenge (LIPS'2008) that took place as a special session at INTERSPEECH 2008 in Brisbane, Australia. The aim of the challenge was to stimulate discussion about the subjective quality assessment of synthesized visual speech, with a view to developing standardized evaluation procedures.

For this Special Issue, all papers selected for publication should include a description of a subjective evaluation experiment that outlines the impact of the proposed synthesis scheme on some subjective measure, such as audiovisual intelligibility, cognitive load, or perceived naturalness. This evaluation metric could be assessed either by participation in the LIPS'2008 challenge or by an independent perceptual experiment.

Before submission authors should carefully read over the journal's Author Guidelines, which are located at http://www.hindawi.com/journals/asmp/guidelines.html. Prospective authors should submit an electronic copy of their complete manuscript through the journal Manuscript Tracking System at http://mts.hindawi.com/ according to the following timetable:

- Manuscript Due: March 1, 2009
- First Round of Reviews: June 1, 2009
- Publication Date: September 1, 2009

Lead Guest Editor

* Gérard Bailly, Speech & Cognition Department, GIPSA-Lab, 38402 Grenoble Cedex, France

Guest Editors

* Sascha Fagel, Speech & Communication Institute, Technische Universität Berlin, 10623 Berlin, Germany
* Barry-John Theobald, School of Computing Sciences, University of East Anglia, Norwich NR4 7TJ, UK

Deadline: 01 March 2009

This is a

event.

Sections

Personal tools

Animating Virtual Speakers or Singers from Audio: Lip-Synching Facial Animation

Animating Virtual Speakers or Singers from Audio: Lip-Synching Facial Animation

Call for Papers