# SingFake: Singing Voice Deepfake Detection

arXiv: https://arxiv.org/abs/2309.07525 · HTML: https://mlsanity.com/paper/2309.07525/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 14 Sep 2023.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild](https://mlsanity.com/paper/2210.02437/) (2022)
- [Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation](https://mlsanity.com/paper/2202.12233/) (2022)
- [End-to-end speaker segmentation for overlap-aware resegmentation](https://mlsanity.com/paper/2104.04045/) (2021)
- [One-class Learning Towards Synthetic Voice Spoofing Detection](https://mlsanity.com/paper/2010.13995/) (2020)
- [Music Demixing Challenge 2021](https://mlsanity.com/paper/2108.13559/) (2021)
- [VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis](https://mlsanity.com/paper/2110.08813/) (2021)
- [SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofing](https://mlsanity.com/paper/2211.02718/) (2022)
- [Learning From Yourself: A Self-Distillation Method for Fake Speech Detection](https://mlsanity.com/paper/2303.01211/) (2023)
- [FSD: An Initial Chinese Dataset for Fake Song Detection](https://mlsanity.com/paper/2309.02232/) (2023)
- [An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems](https://mlsanity.com/paper/2104.01320/) (2021)
- [Singing Beat Tracking With Self-supervised Front-end and Linear Transformers](https://mlsanity.com/paper/2208.14578/) (2022)

## Built on by (most cited first, 21 of 21)

- [SONICS: Synthetic Or Not -- Identifying Counterfeit Songs](https://mlsanity.com/paper/2408.14080/) (2024)
- [Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing](https://mlsanity.com/paper/2504.05657/) (2025)
- [Harder or Different? Understanding Generalization of Audio Deepfake Detection](https://mlsanity.com/paper/2406.03512/) (2024)
- [AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge](https://mlsanity.com/paper/2408.17352/) (2024)
- [Detecting music deepfakes is easy but actually hard](https://mlsanity.com/paper/2405.04181/) (2024)
- [Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024](https://mlsanity.com/paper/2409.02302/) (2024)
- [Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofing](https://mlsanity.com/paper/2409.08346/) (2024)
- [From Real to Cloned Singer Identification](https://mlsanity.com/paper/2407.08647/) (2024)
- [SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan](https://mlsanity.com/paper/2405.05244/) (2024)
- [Deepfake Detection of Singing Voices With Whisper Encodings](https://mlsanity.com/paper/2501.18919/) (2025)
- [AI-Generated Song Detection via Lyrics Transcripts](https://mlsanity.com/paper/2506.18488/) (2025)
- [Training-Free Multi-Step Audio Source Separation](https://mlsanity.com/paper/2505.19534/) (2025)
- [Melody or Machine: Detecting Synthetic Music with Dual-Stream Contrastive Learning](https://mlsanity.com/paper/2512.00621/) (2025)
- [Alethia: A Foundational Encoder for Voice Deepfakes](https://mlsanity.com/paper/2605.00251/) (2026)
- [A New Approach to Voice Authenticity](https://mlsanity.com/paper/2402.06304/) (2024)
- [Spectrogram-Based Detection of Auto-Tuned Vocals in Music Recordings](https://mlsanity.com/paper/2403.05380/) (2024)
- [Application of ASV for Voice Identification after VC and Duration Predictor Improvement in TTS Models](https://mlsanity.com/paper/2406.19243/) (2024)
- [Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models](https://mlsanity.com/paper/2409.14131/) (2024)
- [Echoes: A semantically-aligned music deepfake detection dataset](https://mlsanity.com/paper/2603.23667/) (2026)
- [HAIM: Human-AI Music Datasets for AI Music Production Tracking Benchmark](https://mlsanity.com/paper/2606.01686/) (2026)
- [Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task](https://mlsanity.com/paper/2608.14916/) (2026)

## Abstract (arXiv)

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 these systems lag significantly behind their performance on speech test data. When trained on SingFake, either using separated vocal tracks or song mixtures, these systems show substantial improvement. However, our evaluations also identify challenges associated with unseen singers, communication codecs, languages, and musical contexts, calling for dedicated research into singing voice deepfake detection. The SingFake dataset and related resources are available at https://www.singfake.org/.