Amanous: Distribution-Switching for Superhuman Piano Density on Disklavier

In one sentence

A hardware-aware composition system for the Yamaha Disklavier that unifies Nancarrow tempo canons, Xenakis-style stochastic distributions and L-system grammars via 'distribution-switching', and pre-compensates velocity-dependent actuation latency.

Abstract

A player piano can strike more keys, across more of the register, and faster than any pianist can reach. Three traditions dominate composition in that region, namely Nancarrow's tempo canons, Xenakis' stochastic distributions, and L-system grammars. They have developed in isolation, and none of them accounts for the instrument itself. A Disklavier does not answer instantly, because a loud note reaches the string sooner than a soft one, so music written as if the mechanism were transparent arrives distorted. We present Amanous, a hardware-aware composition system for the Yamaha Disklavier that unifies the three traditions through distribution-switching, in which each grammar symbol selects an entire distributional regime rather than adjusting parameters within a fixed one. A four-layer pipeline carries a symbol from grammar to actuation-ready MIDI. An L-system fixes the macro-form, each symbol is mapped to distributions and a tempo-canon ratio, events are sampled and time-scaled, and a hardware layer pre-compensates velocity-dependent latency and enforces the key-reset time. Convergence points close a feedback loop, letting the music's own temporal structure trigger the next switch. Sections from different symbols remain statistically separable at the output, and ablating the L-system, the tempo canon, or the hardware compensation each degrades a distinct property. Under the modelled latency curve, pre-compensation takes the mean onset error from roughly 18 ms to below the instrument's 1 ms scanning resolution. Structured and random textures are most separable near 25 notes/s, and melodic metrics lose their discriminative power over the 40-100 notes/s band, above which the difference is consistent with distributional content rather than melodic order. All results are computational, nothing was played or measured on an instrument, and a psychoacoustic protocol is proposed for future work.

Source: arXiv:2603.16890

Key facts

• Latency pre-compensation: mean onset error ≈18 ms → below the 1 ms scanning resolution (modelled latency curve)
• Structured vs. random textures most separable near 25 notes/s; melodic metrics lose discriminative power over 40–100 notes/s
• All results are computational; no instrument measurements

When this paper is relevant

• You compose for player piano / Disklavier at densities beyond human playability
• You want to combine algorithmic-composition traditions (Nancarrow, Xenakis, L-systems) in one system
• You need to compensate velocity-dependent mechanical latency of a MIDI-driven instrument
• You ask at what note density melodic structure stops being perceptible/measurable

Scope: No measurements on a physical instrument and no listening study; results are computational.

Cite

Joonhyung Bae (2026). Amanous: Distribution-Switching for Superhuman Piano Density on Disklavier. Journal of Creative Music Systems, Vol. 10, No. 1, University of Huddersfield Press, 2026. https://arxiv.org/abs/2603.16890

@article{Bae2026amanous,
  title = {Amanous: Distribution-Switching for Superhuman Piano Density on Disklavier},
  author = {Joonhyung Bae},
  journal = {Journal of Creative Music Systems, Vol. 10, No. 1, University of Huddersfield Press, 2026},
  year = {2026},
  eprint = {2603.16890},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.16890}
}

Machine-readable copy: /papers/amanous-2026.md