Metraipolis › archive › dc_4e6c788100dd
A Stem-Agnostic Approach to Hybrid AI Music Detection — arXiv:2609.26956
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26956
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:39:39.010Z
- SHA-256 of the archived text
fe0661ddb6dcc364a8d7b725fdcc7f1136feaab7a3bfba8b885c468400a4cf41- Stable URL of this page
https://metraipolis.com/documento/dc_4e6c788100dd
How to cite
A Stem-Agnostic Approach to Hybrid AI Music Detection — arXiv:2609.26956 — arXiv (en), https://arxiv.org/abs/2609.26956 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e6c788100dd (Metraipolis archive dc_4e6c788100dd, sha256 fe0661ddb6dcc364a8d7b725fdcc7f1136feaab7a3bfba8b885c468400a4cf41)
BibTeX
@misc{dc4e6c788100dd,
title = {A Stem-Agnostic Approach to Hybrid AI Music Detection — arXiv:2609.26956},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26956},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e6c788100dd; sha256 fe0661ddb6dcc364a8d7b725fdcc7f1136feaab7a3bfba8b885c468400a4cf41},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26956. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The inclusion of generative audio in the music production process has led to an increase in hybrid music tracks that blend authentic human performances with AI-generated stems, challenging traditional AI music detectors which operate in a binary setting. In this work, we propose a stem-agnostic framework for identifying synthetic audio sources within hybrid musical mixtures. We introduce the inspectrogram, a novel time-frequency representation that maps localized probabilities of synthetic content across the audio spectrum. By combining the inspectrogram with a Wiener filter estimating target stem energy dominance, a single CNN model evaluates whether the specific stem is generated. Trained on rendered hybrid mixtures and evaluated across various stem classes, our model achieves strong performance on high-frequency sources such as vocals, drums, and guitar, but struggles on the low-frequency, narrow-band bass. We conclude that the quality of separation impacts the detection accuracy and identify source separation as a primary bottleneck and a crucial direction for future research. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in eess.AS). Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.26956 — 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 2026-10-08T13:17:01.862Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).