eduzhai > Applied Sciences > Engineering >

Extrapolating false alarm rates in automatic speaker verification

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Automatic speaker verification (ASV) vendors and corpus providers would bothbenefit from tools to reliably extrapolate performance metrics for largespeaker populations without collecting new speakers. We address false alarmrate extrapolation under a worst-case model whereby an adversary identifies theclosest impostor for a given target speaker from a large population. Our modelsare generative and allow sampling new speakers. The models are formulated inthe ASV detection score space to facilitate analysis of arbitrary ASV systems.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...