DeepAI AI Chat
Log In Sign Up

A Probabilistic Fusion Framework for Spoofing Aware Speaker Verification

02/10/2022
by   You Zhang, et al.
University of Rochester
0

The performance of automatic speaker verification (ASV) systems could be degraded by voice spoofing attacks. Most existing works aimed to develop standalone spoofing countermeasure (CM) systems. Relatively little work targeted at developing an integrated spoofing aware speaker verification (SASV) system. In the recent SASV challenge, the organizers encourage the development of such integration by releasing official protocols and baselines. In this paper, we build a probabilistic framework for fusing the ASV and CM subsystem scores. We further propose fusion strategies for direct inference and fine-tuning to predict the SASV score based on the framework. Surprisingly, these strategies significantly improve the SASV equal error rate (EER) from 19.31 challenge. We verify the effectiveness of our proposed components through ablation studies and provide insights with score distribution analysis.

READ FULL TEXT
01/25/2022

SASV Challenge 2022: A Spoofing Aware Speaker Verification Challenge Evaluation Plan

ASV (automatic speaker verification) systems are intrinsically required ...
04/21/2022

Baseline Systems for the First Spoofing-Aware Speaker Verification Challenge: Score and Embedding Fusion

Deep learning has brought impressive progress in the study of both autom...
03/29/2022

Spoofing-Aware Speaker Verification by Multi-Level Fusion

Recently, many novel techniques have been introduced to deal with spoofi...
09/01/2021

ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan

The automatic speaker verification spoofing and countermeasures (ASVspoo...
03/21/2022

Spoofing-Aware Speaker Verification with Unsupervised Domain Adaptation

In this paper, we initiate the concern of enhancing the spoofing robustn...
02/24/2022

Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation

The performance of spoofing countermeasure systems depends fundamentally...