Auditory-Visual Speech Processing (AVSP) 2013

Annecy, France
August 29 - September 1, 2013

Mixing Faces And Voices: A Study of the Influence of Faces and Voices on Audiovisual Intelligibility

Jérémy Miranda, Slim Ouni

Université de Lorraine. LORIA. UMR7503. Villers-lès-Nancy. France

This study examined the influence of mixing faces and voices on the audiovisual intelligibility. The goal is to study the effect of combining two sources of information on the audiovisual intelligibility. Cross-talker dubbing was performed between faces and voices of 10 meaningful sentences pronounced by 10 talkers: 5 females and 5 males. Human subjects were asked to rate the articulation of the output videos. Comparisons were made between results of original and dubbed video. Almost across all the combinations, the audiovisual intelligibility was acceptable. The intelligibility of the speakers varied, however. We observed an influence of the audio/visual channel on the overall intelligibility that can increase or decrease depending the intelligibility results of this channel.

Full Paper

Bibliographic reference.  Miranda, Jérémy / Ouni, Slim (2013): "Mixing faces and voices: a study of the influence of faces and voices on audiovisual intelligibility", In AVSP-2013, 135-140.