SONICS: Synthetic Or Not - Identifying Counterfeit Songs

ICLR 2025
Md Awsafur Rahman1,*,  Zaber Ibn Abdul Hakim2,*,  Najibul Haque Sarker2,*,  Bishmoy Paul3,*,  Shaikh Anowarul Fattah4
1UC Santa Barbara,  2Virginia Tech,  3Santa Clara University,  4BUET
*Equal Contribution
Paper Code Demo Song Arena Dataset Dataset Model arXiv
Project Teaser

Proposed Spectro-Temporal Tokens Transformer (SpecTTTra) model. First, the input mel-spectrogram undergoes separate temporal and spectral slicing to generate corresponding clips, which are tokenized into temporal and spectral tokens using separate tokenizers. Next, separate positional embeddings are added to these tokens, which are then passed through a Transformer encoder. The resulting globally contextualized features are then average pooled and finally passed to the classifier.

Abstract

The recent surge in AI-generated songs presents exciting possibilities and challenges. These innovations necessitate the ability to distinguish between human-composed and synthetic songs to safeguard artistic integrity and protect human musical artistry. Existing research and datasets in fake song detection only focus on singing voice deepfake detection (SVDD), where the vocals are AI-generated but the instrumental music is sourced from real songs. However, these approaches are inadequate for detecting contemporary end-to-end artificial songs where all components (vocals, music, lyrics, and style) could be AI-generated. Additionally, existing datasets lack music-lyrics diversity, long-duration songs, and open-access fake songs. To address these gaps, we introduce SONICS, a novel dataset for end-to-end Synthetic Song Detection (SSD), comprising over 97k songs (4,751 hours) with over 49k synthetic songs from popular platforms like Suno and Udio. Furthermore, we highlight the importance of modeling long-range temporal dependencies in songs for effective authenticity detection, an aspect entirely overlooked in existing methods. To utilize long-range patterns, we introduce SpecTTTra, a novel architecture that significantly improves time and memory efficiency over conventional CNN and Transformer-based models. In particular, for long audio samples, our top-performing variant outperforms ViT by 8% F1 score while being 38% faster and using 26% less memory. Additionally, in comparison with ConvNeXt, our model achieves 1% gain in F1 score with 20% boost in speed and 67% reduction in memory usage.

Data Generation Pipeline

--> -->

Benchmarks

--> --> -->

BibTeX

@inproceedings{rahman2024sonics,
        title={SONICS: Synthetic Or Not - Identifying Counterfeit Songs},
        author={Rahman, Md Awsafur and Hakim, Zaber Ibn Abdul and Sarker, Najibul Haque and Paul, Bishmoy and Fattah, Shaikh Anowarul},
        booktitle={International Conference on Learning Representations (ICLR)},
        year={2025},
      }