Universal Music Representations? Evaluating Foundation Models on World Music Corpora
This addresses the problem of evaluating foundation models' generalization across diverse musical traditions for music information retrieval researchers, though it is incremental in benchmarking existing models.
The paper evaluated five audio foundation models on six world music corpora to assess cross-cultural generalization, finding that larger models typically performed better on non-Western music but declined for culturally distant traditions, with their approaches achieving state-of-the-art performance on five out of six datasets.
Foundation models have revolutionized music information retrieval, but questions remain about their ability to generalize across diverse musical traditions. This paper presents a comprehensive evaluation of five state-of-the-art audio foundation models across six musical corpora spanning Western popular, Greek, Turkish, and Indian classical traditions. We employ three complementary methodologies to investigate these models' cross-cultural capabilities: probing to assess inherent representations, targeted supervised fine-tuning of 1-2 layers, and multi-label few-shot learning for low-resource scenarios. Our analysis shows varying cross-cultural generalization, with larger models typically outperforming on non-Western music, though results decline for culturally distant traditions. Notably, our approaches achieve state-of-the-art performance on five out of six evaluated datasets, demonstrating the effectiveness of foundation models for world music understanding. We also find that our targeted fine-tuning approach does not consistently outperform probing across all settings, suggesting foundation models already encode substantial musical knowledge. Our evaluation framework and benchmarking results contribute to understanding how far current models are from achieving universal music representations while establishing metrics for future progress.