On the FakeMusicCaps benchmark, an ImageNet-pretrained ResNet18 trained on mel spectrograms distinguishes human from AI-generated music with about 88% F1, and stays above 80% F1 on clips with pitch and tempo changes, though the robustness test is weaker than claimed.
GTZAN – Mel Spectrogram + Resnet18
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Detecting Musical Deepfakes
On the FakeMusicCaps benchmark, an ImageNet-pretrained ResNet18 trained on mel spectrograms distinguishes human from AI-generated music with about 88% F1, and stays above 80% F1 on clips with pitch and tempo changes, though the robustness test is weaker than claimed.