ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:XDOUOI4Xrecord.jsonopen to challenge →
read the original abstract
ASVspoof 5 is the fifth edition in a series of challenges that promote the study of speech spoofing and deepfake attacks, and the design of detection solutions. Compared to previous challenges, the ASVspoof 5 database is built from crowdsourced data collected from a vastly greater number of speakers in diverse acoustic conditions. Attacks, also crowdsourced, are generated and tested using surrogate detection models, while adversarial attacks are incorporated for the first time. New metrics support the evaluation of spoofing-robust automatic speaker verification (SASV) as well as stand-alone detection solutions, i.e., countermeasures without ASV. We describe the two challenge tracks, the new database, the evaluation metrics, baselines, and the evaluation platform, and present a summary of the results. Attacks significantly compromise the baseline systems, while submissions bring substantial improvements.
This paper has not been read by Pith yet.
Forward citations
Cited by 12 Pith papers
-
Probing-Guided Layer Selection from Self-Supervised Speech Models for Generalizable Audio Deepfake Detection
Probing-guided selection of depth zones from frozen SSL speech models yields compact classifiers with 28% relative EER improvement on cross-domain deepfake detection tasks.
-
MixFake: Benchmarking and Enhancing Audio Deepfake Detection in Diverse Real-world Mixed Audio
MixFake is a new benchmark for mixed-authenticity audio and a multi-stream prompt tuning method achieves 0.95% EER foreground and 7.72% absolute gain in complex background deepfake detection.
-
Towards Trustworthy Audio Deepfake Detection: A Systematic Framework for Diagnosing and Mitigating Gender Bias
A diagnosis-first framework for gender bias in audio deepfake detection identifies acoustic representation differences and feature leakage as sources, with per-gender threshold adjustment reducing unfairness by 54-75%...
-
Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages
Introduces the Indic-CodecFake dataset for Indic codec deepfakes and SATYAM, a novel hyperbolic ALM that outperforms baselines through dual-stage semantic-prosodic fusion using Bhattacharya distance.
-
EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection
EchoFake is a new replay-aware dataset combining zero-shot TTS deepfakes and physical replay recordings to improve generalization of speech deepfake detection models over existing lab-focused datasets.
-
Bridging the Age Gap: Towards Detecting Neural Audio Codec Synthesized Elderly Speech Deepfake
Defines ECFD task, releases ECF dataset, demonstrates poor generalization of prior detectors to elderly speech, and introduces BONSAI fusion of LanguageBind and ImageBind achieving 1.66% average EER.
-
FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors
FoeGlass is a black-box red-teaming method that leverages LLM in-context learning with diversity-based prompting to generate adversarial audio samples, raising false negative rates of ADD models by up to 94% over baselines.
-
Alethia: A Foundational Encoder for Voice Deepfakes
Alethia is a pretrained audio encoder using continuous embedding prediction and generative flow-matching reconstruction that outperforms existing speech foundation models on voice deepfake tasks with better robustness...
-
ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks
ProSDD learns speaker-conditioned prosodic variation from real speech via supervised masked prediction and jointly optimizes it with spoof detection, cutting EER substantially on ASVspoof 2024 and emotional datasets.
-
Gender Fairness in Audio Deepfake Detection: Performance and Disparity Analysis
Fairness metrics uncover gender disparities in audio deepfake detection error distributions that standard Equal Error Rate metrics obscure.
-
I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors
An experiment shows humans detect fully synthetic speech below chance but exhibit implicit discrimination via quality ratings in a localization task with trust cue manipulations.
-
AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan
AT-ADD introduces standardized tracks and datasets for evaluating audio deepfake detectors on speech under real-world conditions and on diverse unknown audio types to promote generalization beyond speech-centric methods.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.