Investigating the Potential of Multi-Stage Score Fusion in Spoofing-Aware Speaker Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kurnaz, Oguzhan, Kinnunen, Tomi, Hanilci, Cemal
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916951124606976
author Kurnaz, Oguzhan
Kinnunen, Tomi
Hanilci, Cemal
author_facet Kurnaz, Oguzhan
Kinnunen, Tomi
Hanilci, Cemal
contents Despite improvements in automatic speaker verification (ASV), vulnerability against spoofing attacks remains a major concern. In this study, we investigate the integration of ASV and countermeasure (CM) subsystems into a modular spoof-aware speaker verification (SASV) framework. Unlike conventional single-stage score-level fusion methods, we explore the potential of a multi-stage approach that utilizes the ASV and CM systems in multiple stages. By leveraging ECAPA-TDNN (ASV) and AASIST (CM) subsystems, we consider support vector machine and logistic regression classifiers to achieve SASV. In the second stage, we integrate their outputs with the original score to revise fusion back-end classifiers. Additionally, we incorporate another auxiliary score from RawGAT (CM) to further enhance our SASV framework. Our approach yields an equal error rate (EER) of 1.30% on the evaluation dataset of the SASV2022 challenge, representing a 24% relative improvement over the baseline system.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12668
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Investigating the Potential of Multi-Stage Score Fusion in Spoofing-Aware Speaker Verification
Kurnaz, Oguzhan
Kinnunen, Tomi
Hanilci, Cemal
Audio and Speech Processing
Despite improvements in automatic speaker verification (ASV), vulnerability against spoofing attacks remains a major concern. In this study, we investigate the integration of ASV and countermeasure (CM) subsystems into a modular spoof-aware speaker verification (SASV) framework. Unlike conventional single-stage score-level fusion methods, we explore the potential of a multi-stage approach that utilizes the ASV and CM systems in multiple stages. By leveraging ECAPA-TDNN (ASV) and AASIST (CM) subsystems, we consider support vector machine and logistic regression classifiers to achieve SASV. In the second stage, we integrate their outputs with the original score to revise fusion back-end classifiers. Additionally, we incorporate another auxiliary score from RawGAT (CM) to further enhance our SASV framework. Our approach yields an equal error rate (EER) of 1.30% on the evaluation dataset of the SASV2022 challenge, representing a 24% relative improvement over the baseline system.
title Investigating the Potential of Multi-Stage Score Fusion in Spoofing-Aware Speaker Verification
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.12668