Conference paper
ON THE USE OF VISUAL INFORMATION FOR IMPROVING AUDIO-BASED SPEAKER RECOGNITION
Abstract
Audio-based speaker identification degrades severely when there is a mismatch between training and test conditions either due to channel or noise. In this paper, we explore various techniques to fuse video based speaker identification with audio-based speaker identification to improve the performance under mismatch conditions.
Related
Conference paper
Privacy enablement in a surveillance system
Conference paper