Lightweight Model Attribution And Detection Of Synthetic Speech Via Audio Residual Fingerprints

Abstract

As speech generation technologies advance, so do risks of impersonation, misinformation, and spoofing. We present a lightweight, training-free approach for detecting synthetic speech and attributing it to its source model. Our method addresses three tasks: (1) single-model attribution in an open-world setting, (2) multi-model attribution in a closed-world setting, and (3) real vs. synthetic speech classification. The core idea is simple: we compute standardized average residuals--the difference between an audio signal and its filtered version--to extract model-agnostic fingerprints that capture synthesis artifacts. Experiments across multiple synthesis systems and languages show AUROC scores above 99%, with strong reliability even when only a subset of model outputs is available. The method maintains high performance under common audio distortions, including echo and moderate background noise, while data augmentation can improve results in more challenging conditions. In addition, out-

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypizarro2024lightweight

Related papers

• Syn-att: Synthetic Speech Attribution Via Semi-supervised Unknown Multi-class Ensemble Of Cnns (2023)0.00
• Distinguishing Neural Speech Synthesis Models Through Fingerprints In Speech Waveforms (2023)2.26
• Combining Automatic Speaker Verification And Prosody Analysis For Synthetic Speech Detection (2022)10.48
• Can Synthetic Audio From Generative Foundation Models Assist Audio Recognition And Speech Modeling? (2024)7.15
• Deep Residual Neural Networks For Audio Spoofing Detection (2019)0.00
• Speech-forensics: Towards Comprehensive Synthetic Speech Dataset Establishment And Analysis (2024)3.58
• The Sound Of Silence: Efficiency Of First Digit Features In Synthetic Audio Detection (2022)7.50
• Single And Multi-speaker Cloned Voice Detection: From Perceptual To Learned Features (2023)9.23