Visual Based Reference for Enhanced Audio-Video Source Extraction

Jack Harris (1, 2) , Naqvi Syed Mohsen (3) , Bertrand Rivet (1) , Jonathon Chambers (2) , Christian Jutten (1)

1 GIPSA-VIBS - GIPSA - Vision and Brain Signal Processing
2 School of Electronic, Electrical and Systems Engineering
3 Advanced Signal Processing Group

This paper addresses the problem of source extraction in a complex scene where only moving audio sources are present. An algorithm using a unique yet simple method avoiding higher-order statistics has been developed. The principle idea of the algorithm is to use a video camera array for locating a moving source whose position is used to isolate a noise reference, and thus allowing noise subtraction from the mixture based on the widely-known Widrow adaptive filtering method, that only uses second-order statistics. This adaptive approach provides an alternative to traditional methods particularly when there is need for a real time implementation.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Jack Harris, Naqvi Syed Mohsen, Bertrand Rivet, Jonathon Chambers, Christian Jutten. Visual Based Reference for Enhanced Audio-Video Source Extraction. IMA - 9th IMA International Conference on Mathematics in Signal Processing, Jan 2012, Birmingham, United Kingdom. pp.n/c. ⟨hal-00781793⟩