Singfake: Singing Voice Deepfake Detection

Abstract

The rise of singing voice synthesis presents critical challenges to artists and industry stakeholders over unauthorized voice usage. Unlike synthesized speech, synthesized singing voices are typically released in songs containing strong background music that may hide synthesis artifacts. Additionally, singing voices present different acoustic and linguistic characteristics from speech utterances. These unique properties make singing voice deepfake detection a relevant but significantly different problem from synthetic speech detection. In this work, we propose the singing voice deepfake detection task. We first present SingFake, the first curated in-the-wild dataset consisting of 28.93 hours of bonafide and 29.40 hours of deepfake song clips in five languages from 40 singers. We provide a train/validation/test split where the test sets include various scenarios. We then use SingFake to evaluate four state-of-the-art speech countermeasure systems trained on speech utterances. We find th

Stats

• citations38
• S2 citations—
• github stars0
• HF likes0
• heat score11.93
• arxiv keyzang2023singfake

Related papers

• Singing Voice Graph Modeling For Singfake Detection (2024)8.09
• Ctrsvdd: A Benchmark Dataset And Baseline Analysis For Controlled Singing Voice Deepfake Detection (2024)0.00
• SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan (2024)0.00
• SONICS: Synthetic Or Not -- Identifying Counterfeit Songs (2024)0.00
• Speech Foundation Model Ensembles For The Controlled Singing Voice Deepfake Detection (ctrsvdd) Challenge 2024 (2024)11.14
• Securing Voice Biometrics: One-shot Learning Approach For Audio Deepfake Detection (2023)9.03
• AUDETER: A Large-scale Dataset For Deepfake Audio Detection In Open Worlds (2025)0.00
• Combining Automatic Speaker Verification And Prosody Analysis For Synthetic Speech Detection (2022)10.48