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

• URL: http://arxiv.org/abs/2606.16612v1
• Date: Mon, 15 Jun 2026 12:02:53 GMT
• Title: Beyond Artifacts: Towards Generalizable Synthetic Song Detection via Music-Intrinsic Features
• Abstract summary: We propose a flexible framework that models music-intrinsic attributes via feature-specific experts and an adaptive Mixture-of-Experts (MoE) module.<n>Experiments show that Sofia learns generator-agnostic representations from music-intrinsic features, improving the F1 score by 18.5 points over the strongest baseline.
• Score: 10.350758083987605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• FIGMA: Towards FIne-Grained Music retrievAl [65.98380295254817]
  Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries.<n>We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens.<n>We propose FIGMA, a multi-view contrastive architecture that addresses this limitation by jointly optimizing global audio-text alignment and frame-level, token-wise alignment.
  arXiv  Detail & Related papers  (2026-06-04T18:05:39Z)
• Fusion Segment Transformer: Bi-Directional Attention Guided Fusion Network for AI-Generated Music Detection [1.7034813545878587]
  We propose an improved version of the Segment Transformer, termed the Fusion Segment Transformer.<n>As in our previous work, we extract content embeddings from short music segments using diverse feature extractors.<n>We enhance the architecture for full-audio AI-generated music detection by introducing a Gated Fusion Layer.
  arXiv  Detail & Related papers  (2026-01-20T06:31:05Z)
• Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control [66.46754271097555]
  We release a fully open-source system for long-form song generation with fine-grained style conditioning.<n>The dataset consists of 116k fully licensed synthetic songs with automatically generated lyrics and style descriptions.<n>We train Muse via single-stage supervised finetuning of a Qwen-based language model extended with discrete audio tokens.
  arXiv  Detail & Related papers  (2026-01-07T14:40:48Z)
• Segment Transformer: AI-Generated Music Detection via Music Structural Analysis [1.7034813545878587]
  We aim to improve the accuracy of AIGM detection by analyzing the structural patterns of music segments.<n>Specifically, to extract musical features from short audio clips, we integrated various pre-trained models.<n>For long audio, we developed a segment transformer that divides music into segments and learns inter-segment relationships.
  arXiv  Detail & Related papers  (2025-09-10T04:56:40Z)
• Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning [69.78158549955384]
  We introduce a novel approach that treats core music theory rules, such as those governing beats and intervals, as programmatic functions.<n>This approach generates verifiable sheet music questions in both textual and visual modalities.<n> Evaluation results on SSMR-Bench highlight the key role reasoning plays in interpreting sheet music.
  arXiv  Detail & Related papers  (2025-09-04T09:42:17Z)
• Evaluating Fake Music Detection Performance Under Audio Augmentations [0.0]
  We construct a dataset consisting of both real and synthetic music generated using several systems.<n>We then apply a range of audio transformations and analyze how they affect classification accuracy.<n>We test the performance of a recent state-of-the-art musical deepfake detection model in the presence of audio augmentations.
  arXiv  Detail & Related papers  (2025-07-07T16:15:02Z)
• Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation [14.156461396686248]
  We introduce an efficient Fine-Grained Guidance (FGG) approach within diffusion models.<n>FGG guides the diffusion models to generate music that aligns more closely with the control and intent of expert composers.<n>This approach empowers diffusion models to excel in advanced applications such as improvisation, and interactive music creation.
  arXiv  Detail & Related papers  (2024-10-11T00:41:46Z)
• MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation [19.878013881045817]
  MusiConGen is a temporally-conditioned Transformer-based text-to-music model. It integrates automatically-extracted rhythm and chords as the condition signal. We show that MusiConGen can generate realistic backing track music that aligns well with the specified conditions.
  arXiv  Detail & Related papers  (2024-07-21T05:27:53Z)
• Simple and Controllable Music Generation [94.61958781346176]
  MusicGen is a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns.
  arXiv  Detail & Related papers  (2023-06-08T15:31:05Z)
• Quantized GAN for Complex Music Generation from Dance Videos [48.196705493763986]
  We present Dance2Music-GAN (D2M-GAN), a novel adversarial multi-modal framework that generates musical samples conditioned on dance videos. Our proposed framework takes dance video frames and human body motion as input, and learns to generate music samples that plausibly accompany the corresponding input.
  arXiv  Detail & Related papers  (2022-04-01T17:53:39Z)
• Lets Play Music: Audio-driven Performance Video Generation [58.77609661515749]
  We propose a new task named Audio-driven Per-formance Video Generation (APVG) APVG aims to synthesize the video of a person playing a certain instrument guided by a given music audio clip.
  arXiv  Detail & Related papers  (2020-11-05T03:13:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.