Revisiting Expressive Timing in Piano Performance at Scale: A Distant Listening, Multi‑Corpus Study

Empirical expressive performance studies are typically performed on small, curated datasets. In this study, we present a large‑scale analysis of expressive timing in classical piano performance using a ‘distant listening’ approach across six MIDI datasets totaling over 600 hours of music. We revisit three core aspects of expressive timing drawn from empirical performance research: (1) the relational invariance of timing patterns with respect to tempo; (2) the influence of score markings, register, and interval consonance on articulation; and (3) the role of asynchrony as a means of expressive accentuation. Our findings indicate that timing patterns do not scale proportionally with tempo; however, weak interactions between tempo and metrical position suggest that both factors jointly contribute to shaping timing patterns. Articulation analysis confirms associations with score markings and register, although the relationship with interval consonance is less consistent. Melody lead tendencies are consistently observed across datasets, though our findings indicate that those occurring on the beat level may primarily reflect dynamic accentuation. Overall, our results provide empirical validation for certain established theories of expressive performance while challenging others, illustrating how large‑scale computational analysis can complement traditional controlled studies by offering broader insights into performance timing.