mlsanityData to 19 Oct 2026

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

arXiv 2509.12668 ↗First posted 16 Sep 2025eess.AScited by 1

On the map: Speech and audio language models → Anti-spoofing and adversarial audio attacks

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 19 Oct 2026). Placed in Anti-spoofing and adversarial audio attacks, one of 11 directions in Speech and audio language models. Builds on 13 of its 18 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

13 of 18 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022On the potential of jointly-optimised solutions to spoofing attack detection and automatic speaker verification1 Sep
  2. 2022The DKU-OPPO System for the 2022 Spoofing-Aware Speaker Verification Challenge15 Jul
  3. 2022Baseline Systems for the First Spoofing-Aware Speaker Verification Challenge: Score and Embedding Fusion21 Apr

Other references · 10

  1. 2018VoxCeleb2: Deep Speaker Recognitioncited by 1,166
  2. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 980
  3. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 238
  4. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 235
  5. 2020Speaker Recognition Based on Deep Learning: An Overviewcited by 93
  6. 2021Multi-Source Domain Adaptation for Object Detectioncited by 22
  7. 2024a-DCF: an architecture agnostic metric with application to spoofing-robust speaker verificationcited by 17
  8. 2022A Probabilistic Fusion Framework for Spoofing Aware Speaker Verificationcited by 11
  9. 2020Multitask Learning and Multistage Fusion for Dimensional Audiovisual Emotion Recognitioncited by 10
  10. 2022Spoofing-Aware Speaker Verification by Multi-Level Fusioncited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Joint Optimization of Speaker and Spoof Detectors for Spoofing-Robust Automatic Speaker Verificationcited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2022Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion
  2. 2024Revisiting and Improving Scoring Fusion for Spoofing-aware Speaker Verification Using Compositional Data Analysis
  3. 2022Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector
  4. 2026Integrated Spoofing-Robust Automatic Speaker Verification via a Three-Class Formulation and LLR
  5. 2022A Comparative Study of Fusion Methods for SASV Challenge 2022 ↗
  6. 2022SA-SASV: An End-to-End Spoof-Aggregated Spoofing-Aware Speaker Verification System
  7. 2024Spoofing-Robust Speaker Verification Using Parallel Embedding Fusion: BTU Speech Group's Approach for ASVspoof5 Challenge
  8. 2023Can spoofing countermeasure and speaker verification systems be jointly optimised?