Extrapolating false alarm rates in automatic speaker verification

08/08/2020
by   Alexey Sholokhov, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/07/2019

Target Speaker Extraction for Overlapped Multi-Talker Speaker Verification

The performance of speaker verification degrades significantly when the ...
research
11/04/2019

Voice Biometrics Security: Extrapolating False Alarm Rate via Hierarchical Bayesian Modeling of Speaker Verification Scores

How secure automatic speaker verification (ASV) technology is? More conc...
research
08/17/2023

Home monitoring for frailty detection through sound and speaker diarization analysis

As the French, European and worldwide populations are aging, there is a ...
research
06/30/2023

VoxWatch: An open-set speaker recognition benchmark on VoxCeleb

Despite its broad practical applications such as in fraud prevention, op...
research
07/01/2022

Automatic Evaluation of Speaker Similarity

We introduce a new automatic evaluation method for speaker similarity as...
research
04/28/2021

Personalized Keyphrase Detection using Speaker and Environment Information

In this paper, we introduce a streaming keyphrase detection system that ...
research
05/30/2023

Towards single integrated spoofing-aware speaker verification embeddings

This study aims to develop a single integrated spoofing-aware speaker ve...

Please sign up or login with your details

Forgot password? Click here to reset