eduzhai > Applied Sciences > Engineering >

Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: State-of-the-art speaker verification models are based on deep learningtechniques, which heavily depend on the handdesigned neural architectures fromexperts or engineers. We borrow the idea of neural architecture search(NAS) forthe textindependent speaker verification task. As NAS can learn deep networkstructures automatically, we introduce the NAS conception into the well-knownx-vector network. Furthermore, this paper proposes an evolutionary algorithmenhanced neural architecture search method called Auto-Vector to automaticallydiscover promising networks for the speaker verification task. The experimentalresults demonstrate our NAS-based model outperforms state-of-the-art speakerverification models.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×