AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

MusicDET: Zero-Shot AI-Generated Music Detection

Chaolei Han, Hongsong Wang, Jie Gui

ICML 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Robust fine-tuning of zero-shot models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train a one-class flow on real music only (zero-shot) instead of discriminative detectors trained on one generatorMusicDET · FakeMusicCaps cross-generatorEER (%): 11.46 -> 4.51Improved
add class-conditional prior with generated samplesMusicDET · FakeMusicCaps cross-generatorEER (%): 4.51 -> 0.89Improved
add class-conditional prior with generated samplesMusicDET · SONICS cross-generatorEER (%): 2.89 -> 0.00Improved
zero-shot MusicDET vs spectrogram baseline Spec-ViTMusicDET · SONICS cross-generatorEER (%): 1.23 -> 2.89Hurt
use multiple frequency bands instead of a single band (ablation)MusicDET · FakeMusicCapsEERImproved
increase prior mean mu_real (ablation)one-class MusicDET · FakeMusicCapsEERImproved
fully fine-tune self-supervised front endW2V2-AASIST · FakeMusicCapsEER (%): 25.80 -> 11.46Improved
fully fine-tune self-supervised front endMERT-AASIST · SONICSEER (%): 18.98 -> 28.89Hurt
hold out jazz or piano subdomain from training (ablation)MusicDET · FakeMusicCapsEER (%): jazz 2.5, piano 4.1No clear effect
apply pitch shifting to test audio (ablation)MusicDET · FakeMusicCaps robustnessEER (%): +40.22 (to 44.73)Hurt
apply white noise to test audio (ablation)MusicDET · FakeMusicCaps robustnessEER (%): +39.6 (to 44.11)Hurt
apply time stretching to test audio (ablation)MusicDET · FakeMusicCaps robustnessEER (%): 2.44 (↓2.07)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy