Single And Multi-speaker Cloned Voice Detection: From Perceptual To Learned Features

Abstract

Synthetic-voice cloning technologies have seen significant advances in recent years, giving rise to a range of potential harms. From small- and large-scale financial fraud to disinformation campaigns, the need for reliable methods to differentiate real and synthesized voices is imperative. We describe three techniques for differentiating a real from a cloned voice designed to impersonate a specific person. These three approaches differ in their feature extraction stage with low-dimensional perceptual features offering high interpretability but lower accuracy, to generic spectral features, and end-to-end learned features offering less interpretability but higher accuracy. We show the efficacy of these approaches when trained on a single speaker's voice and when trained on multiple voices. The learned features consistently yield an equal error rate between 0% and 4%, and are reasonably robust to adversarial laundering.

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keybarrington2023single

Related papers

• Securing Voice-driven Interfaces Against Fake (cloned) Audio Attacks (2019)9.92
• Neural Voice Cloning With A Few Samples (2018)0.00
• Defense Against Synthetic Speech: Real-time Detection Of RVC Voice Conversion Attacks (2025)0.00
• Data Efficient Voice Cloning For Neural Singing Synthesis (2019)10.07
• One-class Learning Towards Synthetic Voice Spoofing Detection (2020)17.31
• Toward Improving Synthetic Audio Spoofing Detection Robustness Via Meta-learning And Disentangled Training With Adversarial Examples (2024)6.77
• Voice Cloning: A Multi-speaker Text-to-speech Synthesis Approach Based On Transfer Learning (2021)0.00
• Securing Voice Biometrics: One-shot Learning Approach For Audio Deepfake Detection (2023)9.03