A Comprehensive Corpus of Biomechanically Constrained Piano Chords: Generation, Analysis, and Implications for Voicing and Psychoacoustics

Mahesh Ramani

cs.SDMar 31, 2026

A Comprehensive Corpus of Biomechanically Constrained Piano Chords: Generation, Analysis, and Implications for Voicing and Psychoacoustics

Authors: Mahesh Ramani

Organizations: Independent

Abstract

I present the generation and analysis of the largest known open-source corpus of playable piano chords (approximately 19.3 million entries). This dataset enumerates the two-handed search space subject to biomechanical constraints (two hands, each with 1.5 octave reach) to an unprecedented extent. To demonstrate the corpus's utility, the relationship between voicing shape and psychoacoustic targets was modeled. Harmonicity proved intrinsic to pitch-class identity: voicing statistics added negligible variance ( $ΔR^2 \approx 0.014\%$ , $p \approx 0.13$ ). Conversely, voicing significantly predicted dissonance ( $ΔR^2 \approx 6.75\%$ , $p \approx 0.0008$ ). Crucially, skewness ( $β\approx +0.145$ ) was approximately 5.8 $\times$ more effective than spread ( $β\approx -0.025$ ) at predicting roughness. The analysis challenges the pedagogical emphasis on spread'': skewness is a stronger predictor of dissonance than spread. This suggests that clarity in open voicings'' is driven less by width than by negative skewness; achieving lower-register clearance by placing wide gaps at the bottom and allowing tighter clustering in the treble. The results demonstrate the corpus's ability to enable future research, especially in areas such as generative modeling, voice-leading topology, and psychoacoustic analysis.

Figures & tables

Figure 1: Residual plot for harmonicity predictions (Model 2). Residuals show no systematic patterns as a function of predicted values, confirming model adequacy. Importantly, the residual distribution remains virtually identical whether voicing moments are included (Model 2) or excluded (Model 1), consistent with the negligible $\Delta R^{2}\approx 0.00014$ .

Figure 2: Permutation test for the contribution of voicing moments to dissonance prediction. The histogram shows the null distribution of $\Delta R^{2}$ values obtained by randomly permuting the residualized voicing features (1,200 iterations). The observed $\Delta R^{2}=0.0675$ falls far in the right tail ( $p\approx 0.0008$ ), strongly rejecting the null hypothesis that voicing shape does not contribute to dissonance beyond pitch-class content.

Figure 3: Actual vs. predicted dissonance values for Model 2 (controls + voicing moments) on the held-out test set. Each point represents one chord (N = 10,000 test chords). The diagonal line represents perfect prediction. The model achieves $R^{2}\approx 0.71$ , demonstrating that voicing shape, when combined with pitch-class content, provides substantial predictive power for psychoacoustic roughness.

PianoCoRe: Combined and Refined Piano MIDI Dataset
May 7, 2026Ilya BorovikMusic Information Retrieval
*Skolkovo Institute of Science and Technology, Moscow, Russia
An audio-to-analysis pipeline with certified transcription for information-theoretic profiling of the piano repertoire
Apr 25, 2026Fred Jalbert-DesforgesComputational Musicology Automatic Music Transcription
Independent Music Analysis Researcher Creator of CYGNUS & LYRA Montreal, Quebec
Dissonance Spectrum explicitly models perceptual frequency interactions for better music understanding
Aug 26, 2026Tianle Wang, Xinyi Tong, Liangke Zhao +7Music Understanding Time-Frequency Analysis
Beijing Institute for General Artificial Intelligence, Beijing, China · Central Conservatory of Music, Beijing, China · Peking University, Beijing, China

May 7, 2026J/K move · Enter open · S save

PianoCoRe: Combined and Refined Piano MIDI Dataset

Ilya Borovik

*Skolkovo Institute of Science and Technology, Moscow, Russia

Music Information Retrieval

Open paper AskPDF arXiv

Symbolic music datasets with matched scores and performances are essential for many music information retrieval (MIR) tasks. Yet, existing resources often cover a narrow range of composers, lack performance variety, omit note-level alignments, or use inconsistent naming formats. This work presents PianoCoRe, a large-scale piano MIDI dataset that unifies and refines major open-source piano corpora. The dataset contains 250,046 performances of 5,625 pieces written by 483 composers, totaling 21,763 h of performed music. PianoCoRe is released in tiered subsets to support different applications: from large-scale analysis and pre-training (PianoCoRe-C and deduplicated PianoCoRe-B) to expressive performance modeling with note-level score alignment (PianoCoRe-A/A*). The note-aligned subset, PianoCoRe-A, provides the largest open-source collection of 157,207 performances aligned to 1,591 scores to date. In addition to the dataset, the contributions are: (1) a MIDI quality classifier for detecting corrupted and score-like transcriptions and (2) RAScoP, an alignment refinement pipeline that cleans temporal alignment errors and interpolates missing notes. The analysis shows that the refinement reduces temporal noise and eliminates tempo outliers. Moreover, an expressive performance rendering model trained on PianoCoRe demonstrates improved robustness to unseen pieces compared to models trained on raw or smaller datasets. PianoCoRe provides a ready-to-use foundation for the next generation of expressive piano performance research.

Abstract

Explore similar work

PianoCoRe: Combined and Refined Piano MIDI Dataset

An audio-to-analysis pipeline with certified transcription for information-theoretic profiling of the piano repertoire

Dissonance Spectrum explicitly models perceptual frequency interactions for better music understanding