# Beyond Artifacts: Towards Generalizable Synthetic Song Detection via Music-Intrinsic Features

arXiv: https://arxiv.org/abs/2606.16612 · HTML: https://mlsanity.com/paper/2606.16612/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 19 of 19)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [YuE: Scaling Open Foundation Models for Long-Form Music Generation](https://mlsanity.com/paper/2503.08638/) (2025)
- [MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization](https://mlsanity.com/paper/2501.01108/) (2025)
- [One-class Learning Towards Synthetic Voice Spoofing Detection](https://mlsanity.com/paper/2010.13995/) (2020)
- [DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion](https://mlsanity.com/paper/2503.01183/) (2025)
- [ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation](https://mlsanity.com/paper/2602.00744/) (2026)
- [SONICS: Synthetic Or Not -- Identifying Counterfeit Songs](https://mlsanity.com/paper/2408.14080/) (2024)
- [CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection](https://mlsanity.com/paper/2406.02438/) (2024)
- [HeartMuLa: A Family of Open Sourced Music Foundation Models](https://mlsanity.com/paper/2601.10547/) (2026)
- [FSD: An Initial Chinese Dataset for Fake Song Detection](https://mlsanity.com/paper/2309.02232/) (2023)
- [A Fourier Explanation of AI-music Artifacts](https://mlsanity.com/paper/2506.19108/) (2025)
- [Fx-Encoder++: Extracting Instrument-Wise Audio Effects Representations from Mixtures](https://mlsanity.com/paper/2507.02273/) (2025)
- [Double Entendre: Robust Audio-Based AI-Generated Lyrics Detection via Multi-View Fusion](https://mlsanity.com/paper/2506.15981/) (2025)
- [Deepfake Detection of Singing Voices With Whisper Encodings](https://mlsanity.com/paper/2501.18919/) (2025)

## Abstract (arXiv)

The rapid advancement of AI music generators highlights the urgent need for reliable Synthetic Song Detection (SSD). Existing SSD methods often rely on low-level artifacts or fixed feature assumptions, struggling to capture generator-agnostic cues. To address this, we propose Sofia (Synthetic-song detection framework via music features), a flexible framework that models music-intrinsic attributes via feature-specific experts and an adaptive Mixture-of-Experts (MoE) module. By configuring Sofia with representative Vocal, Audio-effect, Global structure features, and their combinations, we present their individual and complementary contributions. To comprehensively evaluate our framework, we further construct MUSIC8K, a challenging benchmark featuring lastest emerging generators and realistic audio perturbations. Experiments show that Sofia learns generator-agnostic representations from music-intrinsic features, improving the F1 score by 18.5 points over the strongest baseline on MUSIC8K-O while maintaining strong robustness.