You are here:

Evaluating the Use of Audio-Visual Speech Synthesis in Pronunciation Training
PROCEEDINGS

, UMIST, United Kingdom

EdMedia + Innovate Learning, in Honolulu, Hawaii, USA ISBN 978-1-880094-48-8 Publisher: Association for the Advancement of Computing in Education (AACE), Waynesville, NC

Abstract

This paper introduces the use of audio-visual speech synthesis for pronunciation training within Computer Assisted Language Learning (CALL) software. It has been proven that speech perception is greatly improved when visual and audio input are combined, this can be used to aid second language learners with pronunciation problems. This work aims to evaluate whether viewing the audio-visual output of a talking head can provide significant pronunciation improvement over an audio only output.

Citation

Voce, J. (2003). Evaluating the Use of Audio-Visual Speech Synthesis in Pronunciation Training. In D. Lassner & C. McNaught (Eds.), Proceedings of ED-MEDIA 2003--World Conference on Educational Multimedia, Hypermedia & Telecommunications (pp. 491-494). Honolulu, Hawaii, USA: Association for the Advancement of Computing in Education (AACE). Retrieved January 18, 2020 from .

Keywords

References

View References & Citations Map

These references have been extracted automatically and may have some errors. Signed in users can suggest corrections to these mistakes.

Suggest Corrections to References