Investigating Prosodic Signatures Via Speech Pre-trained Models For Audio Deepfake Source Attribution

Abstract

In this work, we investigate various state-of-the-art (SOTA) speech pre-trained models (PTMs) for their capability to capture prosodic signatures of the generative sources for audio deepfake source attribution (ADSD). These prosodic characteristics can be considered one of major signatures for ADSD, which is unique to each source. So better is the PTM at capturing prosodic signs better the ADSD performance. We consider various SOTA PTMs that have shown top performance in different prosodic tasks for our experiments on benchmark datasets, ASVSpoof 2019 and CFAD. x-vector (speaker recognition PTM) attains the highest performance in comparison to all the PTMs considered despite consisting lowest model parameters. This higher performance can be due to its speaker recognition pre-training that enables it for capturing unique prosodic characteristics of the sources in a better way. Further, motivated from tasks such as audio deepfake detection and speech recognition, where fusion of PTMs rep

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyphukan2024investigating

Related papers

• Heterogeneity Over Homogeneity: Investigating Multilingual Speech Pre-trained Models For Detecting Audio Deepfake (2024)8.09
• Pitch Imperfect: Detecting Audio Deepfakes Through Acoustic Prosodic Analysis (2025)0.00
• Combining Automatic Speaker Verification And Prosody Analysis For Synthetic Speech Detection (2022)10.48
• Adversarial Attacks On Audio Deepfake Detection: A Benchmark And Comparative Study (2025)0.00
• Securing Voice Biometrics: One-shot Learning Approach For Audio Deepfake Detection (2023)9.03
• Lightweight Model Attribution And Detection Of Synthetic Speech Via Audio Residual Fingerprints (2024)0.00
• Deep Residual Neural Networks For Audio Spoofing Detection (2019)0.00
• Detection Of Cross-dataset Fake Audio Based On Prosodic And Pronunciation Features (2023)0.00