Learning to Predict Performance-induced Emotion Differences in Classical Piano Music

2026-07-30

AI Summary

This study addresses the challenge of isolating expressive performance nuances from compositional structure to model subtle emotional variations in classical piano music. Focusing on six commercial recordings of Book I of Bach’s *Well-Tempered Clavier*, the authors extract performance-only features and propose a Delta-VA relative regression framework to predict continuous deviations in valence and arousal relative to an “average performance.” A novel geometric evaluation metric is introduced to quantify directional consistency of emotional differences across performances. Experimental results demonstrate that the model accurately captures the direction of emotional variation but systematically underestimates its intensity, revealing a current limitation in modeling the magnitude of expressive dynamics.

Abstract

Music is often used as a medium for communicating emotion, with performers shaping perceived affect through interpretation. This study addresses the challenge of identifying and predicting subtle changes in perceived emotion that are exclusively due to differences in performance. We focus on classical solo piano music, using a set of 6 commercial recordings of Bach's Well-Tempered Clavier Book I, annotated in terms of valence and arousal. By encoding the recordings through performance-specific features only, we isolate performance information from aspects of the composition itself, which tend to dominate the overall perceived emotional category. A preliminary analysis validates that these features vary meaningfully across performers. We then propose a relative regression framework, Delta-VA, to predict deviations in valence-arousal relative to an ``average'' performance, thereby focusing on the changes in emotion brought about by a specific way of playing a piece. In addition to the standard $R^2$ regression score, we introduce geometric evaluation metrics to assess the preservation of pairwise differences between performances. Results indicate high directional consistency with the ground truth, but also a compression in prediction magnitude, indicating that the model tends to underestimate expressive performance effects.

Problem

• performance-induced emotion
• classical piano music
• valence-arousal prediction
• expressive performance
• emotion perception

Innovation

• performance-induced emotion
• relative regression
• Delta-VA
• expressive performance modeling
• valence-arousal prediction