Audio Visual Integration with Competing Sources in the Framework of Audio Visual Speech Scene Analysis.

Abstract

We introduce "Audio-Visual Speech Scene Analysis" (AVSSA) as an extension of the two-stage Auditory Scene Analysis model towards audiovisual scenes made of mixtures of speakers. AVSSA assumes that a coherence index between the auditory and the visual input is computed prior to audiovisual fusion, enabling to determine whether the sensory inputs should be… (More)
DOI: 10.1007/978-3-319-25474-6_42

Topics

Cite this paper

@article{Ganesh2016AudioVI, title={Audio Visual Integration with Competing Sources in the Framework of Audio Visual Speech Scene Analysis.}, author={Attigodu C. Ganesh and Fr{\'e}d{\'e}ric Berthommier and Jean-Luc Schwartz}, journal={Advances in experimental medicine and biology}, year={2016}, volume={894}, pages={399-408} }