eduzhai > Applied Sciences > Engineering >

Audio-visual Speaker Recognition with a Cross-modal Discriminative Network

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Audio-visual speaker recognition is one of the tasks in the recent 2019 NISTspeaker recognition evaluation (SRE). Studies in neuroscience and computerscience all point to the fact that vision and auditory neural signals interactin the cognitive process. This motivated us to study a cross-modal network,namely voice-face discriminative network (VFNet) that establishes the generalrelation between human voice and face. Experiments show that VFNet providesadditional speaker discriminative information. With VFNet, we achieve 16.54 equal error rate relative reduction over the score level fusion audio-visualbaseline on evaluation set of 2019 NIST SRE.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×