Visual speech and coarticulation effects

  • Authors:

  • Hans H. Bothe;Frauke Rieger

  • Affiliations:

  • Technical University of Berlin, Department of Electronics, Berlin;Technical University of Berlin, Department of Electronics, Berlin

  • Venue:
  • ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: image and multidimensional signal processing - Volume V
  • Year:
  • 1993

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents the state of the art of a computer animation program showing realistic movements of an abstracted speaker's face. For this purpose, video tapes with prototypic speakers have been recorded and analyzed in order to investigate the fundamental correlation between phonetic sequences of given German texts and the corresponding visual movements of articulation. Considering coarticulation effects, a 2D-motion model was set up on a commercial PC using a set of 38 key-pictures and calculating interim frames. The coordinated movements of the visible speech synthesis cover the lips, the teeth and the tip of the tongue. The possible text input is based on an open vocabulary. The program is designed to be a training aid for lipreading for hearing impaired people.