Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals

Abstract

Recent years have seen growing efforts to develop spoofing countermeasures (CMs) to protect automatic speaker verification (ASV) systems from being deceived by manipulated or artificial inputs. The reliability of spoofing CMs is typically gauged using the equal error rate (EER) metric. The primitive EER fails to reflect application requirements and the impact of spoofing and CMs upon ASV and its use as a primary metric in traditional ASV research has long been abandoned in favour of risk-based approaches to assessment. This paper presents several new extensions to the tandem detection cost function (t-DCF), a recent risk-based approach to assess the reliability of spoofing CMs deployed in tandem with an ASV system. Extensions include a simplified version of the t-DCF with fewer parameters, an analysis of a special case for a fixed ASV system, simulations which give original insights into its interpretation and new analyses using the ASVspoof 2019 database. It is hoped that adoption of the t-DCF for the CM assessment will help to foster closer collaboration between the anti-spoofing and ASV research communities.

arXiv commentPublished in IEEE/ACM Transactions on Audio, Speech, and Language Processing (doi updated)

References in corpus (1)

• VoxCeleb: a large-scale speaker identification dataset

Cited by in corpus (21)

• ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech
• ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan
• UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021
• A Survey on Speech Deepfake Detection
• Optimizing Tandem Speaker Verification and Anti-Spoofing Systems
• Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms
• Generalizing Speaker Verification for Spoof Awareness in the Embedding Space
• Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples
• Audio Anti-spoofing Using a Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning
• GMM-ResNet2: Ensemble of Group ResNet Networks for Synthetic Speech Detection
• End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection
• Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verification
• Spoofing Attack Detection using the Non-linear Fusion of Sub-band Classifiers
• End-to-end anti-spoofing with RawNet2
• Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
• t-EER: Parameter-Free Tandem Evaluation of Countermeasures and Biometric Comparators
• Benchmarking and challenges in security and privacy for voice biometrics
• A Tandem Framework Balancing Privacy and Security for Voice User Interfaces
• An Initial Investigation for Detecting Partially Spoofed Audio
• Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector
• Raw Differentiable Architecture Search for Speech Deepfake and Spoofing Detection