Auditory-Visual Speech Processing (AVSP'99)

August 7-10, 1999
Santa Cruz, CA, USA

On the Use of Visual Information for Improving Audio-Based Speaker Recognition

Andrew Senior, Chalapathy V. Neti, Benoit Maison

IBM T. J. Watson Research Center, Yorktown Heights, NY, USA

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.


Full Paper

Bibliographic reference.  Senior, Andrew / Neti, Chalapathy V. / Maison, Benoit (1999): "On the use of visual information for improving audio-based speaker recognition", In AVSP-1999, paper #18.