Five audio foundation models are evaluated across six Western and non-Western music corpora, showing a consistent Western-centric bias and only limited generalization to culturally distant traditions.
Overall, Qwen2-Audio achieves the highest performance with 88.59% ROC-AUC and 56.48% mAP in Probing, further improving to 89.37% ROC-AUC and 58.73% mAP after fine-tuning
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
-
Universal Music Representations? Evaluating Foundation Models on World Music Corpora
Five audio foundation models are evaluated across six Western and non-Western music corpora, showing a consistent Western-centric bias and only limited generalization to culturally distant traditions.