Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition
For music information retrieval researchers, this work identifies jazz standard recognition as a stress test for music representation models, but the results are incremental and domain-specific.
The paper evaluates pretrained music embeddings for cross-performance jazz standard recognition, finding that from-scratch models overfit while pretrained embeddings improve top-k results but remain sensitive to performer identity, partially mitigated by contrastive projection.
Recognizing jazz standards from audio is a challenging form of tune-level music retrieval: different performances of the same standard may vary in tempo, key, arrangement, instrumentation, improvisational content, and even whether the head melody is present. We study this problem using a curated subset of the Jazz Trio Database designed for cross-performance standard recognition. We compare a from-scratch trained Harmonic CNN baseline against frozen pretrained music representations from recent music understanding foundation models, using both supervised probing and nearest-neighbor retrieval. Our results suggest that from-scratch spectrogram models overfit strongly to training performances, while pretrained embeddings provide better top-$k$ results but are sensitive to performer identity, which can be partially reduced with a lightweight contrastive projection. Our findings motivate jazz standard recognition as a useful stress test for music representation models and as a step toward retrieval-based standard identification. Project page: https://github.com/cagries/tipofmyear.