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

arXiv: https://arxiv.org/abs/2607.28876 · HTML: https://mlsanity.com/paper/2607.28876/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times](https://mlsanity.com/paper/2010.01815/) (2020)
- [Automatic Piano Transcription with Hierarchical Frequency-Time Transformer](https://mlsanity.com/paper/2307.04305/) (2023)
- [Partitura: A Python Package for Symbolic Music Processing](https://mlsanity.com/paper/2206.01071/) (2022)
- [A Data-Driven Analysis of Robust Automatic Piano Transcription](https://mlsanity.com/paper/2402.01424/) (2024)
- [Scoring Time Intervals using Non-Hierarchical Transformer For Automatic Piano Transcription](https://mlsanity.com/paper/2404.09466/) (2024)
- [DExter: Learning and Controlling Performance Expression with Diffusion Models](https://mlsanity.com/paper/2406.14850/) (2024)
- [Regression-based music emotion prediction using triplet neural networks](https://mlsanity.com/paper/2001.09988/) (2020)
- [Towards Musically Informed Evaluation of Piano Transcription Models](https://mlsanity.com/paper/2406.08454/) (2024)
- [On Perceived Emotion in Expressive Piano Performance: Further Experimental Evidence for the Relevance of Mid-level Perceptual Features](https://mlsanity.com/paper/2107.13231/) (2021)
- [Sound and Music Biases in Deep Music Transcription Models: A Systematic Analysis](https://mlsanity.com/paper/2512.14602/) (2025)
- [Stacked Convolutional and Recurrent Neural Networks for Music Emotion Recognition](https://mlsanity.com/paper/1706.02292/) (2017)

## Abstract (arXiv)

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 R2 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.