Estimation of Playable Piano Fingering by Pitch-difference Fingering Matching Model

TL;DR

This paper introduces a novel pitch-difference sequence and fingering matching model for piano fingering estimation, improving playability and matching accuracy over existing models by incorporating pitch relationships and prior knowledge.

Contribution

The paper proposes a new PdF matching model that integrates pitch-difference sequences and prior fingering knowledge, enhancing the estimation of playable piano fingering.

Findings

Matching rate increases by 3% over state-of-the-art models

All scores' fingering become playable with the new model

Introduces IFR as a new evaluation index for fingering models

Abstract

The existing piano fingering labeling statistical models usually consider the constraints among the fingers and the correlation between fingering and notes, and rarely include the relationship among the notes directly. The limited learned finger-transfer rules often cause that some parts of the fingering cannot be playable in fact. And traditional models often adopt the original notes, which cannot help to explore the mapping nature between the pitches and fingering. Inspired from manual-ly annotation which acquire the fingering knowledge directly from pitch-difference, we proposed a pitch-difference sequence and fingering (PdF) matching model. And to get playable fingering, be-sides learned finger-transfer rules, prior finger-transfer knowledge is especially combined into the model. In order to characterize the playable performance of the model, we also presented a new evaluation index named incapable-performing fingering rate (IFR). Comprehensive experimental re-sults show that compared with the existing state-of-the-art third-order hidden Markov labeling model, the general and the highest matching rate of our model increases by 3% and 1.6% respective-ly, and the fingering for all scores can be playable.