Metraipolis › archive › dc_f87baeb0fa4b

Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task — arXiv:2608.14916

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14916
License (as archived)
CC0-1.0
Archived
2026-10-18T17:55:03.144Z
SHA-256 of the archived text
88e1b208b4a3eb84ba6c3b74a67190b0ed358216878074e07720b045cfcc3f4b
Stable URL of this page
https://metraipolis.com/documento/dc_f87baeb0fa4b

How to cite

Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task — arXiv:2608.14916 — arXiv (en), https://arxiv.org/abs/2608.14916 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f87baeb0fa4b (Metraipolis archive dc_f87baeb0fa4b, sha256 88e1b208b4a3eb84ba6c3b74a67190b0ed358216878074e07720b045cfcc3f4b)
BibTeX
@misc{dcf87baeb0fa4b,
  title = {Distinguishing AI-Generated Music from Edited Audio as a Hard-Negative Robustness Task — arXiv:2608.14916},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14916},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f87baeb0fa4b; sha256 88e1b208b4a3eb84ba6c3b74a67190b0ed358216878074e07720b045cfcc3f4b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14916. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI-generated music detectors are commonly evaluated against original songs, but real-world uploads are often remixed, re-encoded, pitch-shifted, or otherwise edited. These edited versions form a difficult negative class: they are not generated by AI, yet they may introduce spectral artifacts that resemble synthetic audio fingerprints. We study this problem as a hard-negative robustness setting for AI-generated music detection, focusing on AI-generated and edited variants derived from the same anchor songs. We compile a YouTube-based dataset of AI, edited, and original variants, using the original tracks only as references, and train a binary AI versus edited detector. Audio is processed as 10-second clips and passed as raw waveforms to a pretrained PaSST spectrogram transformer. To reduce leakage, all splits are performed by anchor song. On the held-out test set, the final video-level system achieves 0.811 balanced accuracy. At clip level, AI-generated clips reach an F1-score of 0.836, while edited clips reach a lower F1-score of 0.720. The results suggest that AI-generated music retains detectable fingerprint-like spectral cues beyond ordinary editing, but the lower edited-class F1-score shows that these cues can still overlap with artifacts from edited audio. Grad-CAM visualizations are used to inspect whether high-confidence predictions rely on localized time-frequency regions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.14916 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T16:29:13.965Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).