Segment Transformer: AI-Generated Music Detection via Music Structural Analysis
Not on the map. Why?
Abstract (arXiv)
Audio and music generation systems have been remarkably developed in the music information retrieval (MIR) research field. The advancement of these technologies raises copyright concerns, as ownership and authorship of AI-generated music (AIGM) remain unclear. Also, it can be difficult to determine whether a piece was generated by AI or composed by humans clearly. To address these challenges, we aim to improve the accuracy of AIGM detection by analyzing the structural patterns of music segments. Specifically, to extract musical features from short audio clips, we integrated various pre-trained models, including self-supervised learning (SSL) models or an audio effect encoder, each within our suggested transformer-based framework. Furthermore, for long audio, we developed a segment transformer that divides music into segments and learns inter-segment relationships. We used the FakeMusicCaps and SONICS datasets, achieving high accuracy in both the short-audio and full-audio detection experiments. These findings suggest that integrating segment-level musical features into long-range temporal analysis can effectively enhance both the performance and robustness of AIGM detection systems.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 39 references that are in the map. First posted on arXiv 10 Sep 2025.
Builds on
32 of 39 references.
References · 32
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2022A ConvNet for the 2020scited by 3,579
- 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
- 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 727
- 2023Simple and Controllable Music Generationcited by 488
- 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretrainingcited by 344
- 2022AudioGen: Textually Guided Audio Generationcited by 295
- 2024Stable Audio Opencited by 197
20 more
- 2023MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Trainingcited by 181
- 2022Pretrained Language Models for Text Generation: A Surveycited by 122
- 2022ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wildcited by 121
- 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 117
- 2023Mustango: Toward Controllable Text-to-Music Generationcited by 100
- 2020Self-training and Pre-training are Complementary for Speech Recognitioncited by 99
- 2023MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategiescited by 94
- 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
- 2021Codified audio language modeling learns useful representations for music information retrievalcited by 64
- 2023ADD 2023: the Second Audio Deepfake Detection Challengecited by 64
- 2023Audio Deepfake Detection: A Surveycited by 50
- 2021Investigating self-supervised front ends for speech spoofing countermeasurescited by 46
- 2024Beat this! Accurate beat tracking without DBN postprocessingcited by 27
- 2022MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learningcited by 22
- 2024SONICS: Synthetic Or Not -- Identifying Counterfeit Songscited by 21
- 2022Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effectscited by 18
- 2024FakeMusicCaps: a Dataset for Detection and Attribution of Synthetic Music Generated via Text-to-Music Modelscited by 13
- 2020Detection of AI-Synthesized Speech Using Cepstral & Bispectral Statisticscited by 9
- 2024Watching the Generative AI Hype Bubble Deflatecited by 8
- 2023On the Effectiveness of Speech Self-supervised Learning for Musiccited by 5
Built on by
Citing papers per year: 2026: 1.
1 paper.