Extrapolating false alarm rates in automatic speaker verification

Alexey Sholokhov, Tomi Kinnunen, Ville Vestman, Kong Aik Lee

Research output: Journal article publicationConference articleAcademic researchpeer-review

1 Citation (Scopus)

Abstract

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

Original languageEnglish
Pages (from-to)4218-4222
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2020-October
DOIs
Publication statusPublished - Oct 2020
Externally publishedYes
Event21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, China
Duration: 25 Oct 202029 Oct 2020

Keywords

  • Black-box attack
  • Closest impostor
  • False alarm rate
  • Implicit generative models
  • PLDA
  • Speaker verification

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'Extrapolating false alarm rates in automatic speaker verification'. Together they form a unique fingerprint.

Cite this