Statistical learning and estimation of piano fingering

Abstract

Automatic estimation of piano fingering is important for understanding the computational process of music performance and applicable to performance assistance and education systems. While a natural way to formulate the quality of fingerings is to construct models of the constraints/costs of performance, it is generally difficult to find appropriate parameter values for these models. Here we study an alternative data-driven approach based on statistical modeling in which the appropriateness of a given fingering is described by probabilities. Specifically, we construct two types of hidden Markov models (HMMs) and their higher-order extensions. We also study deep neural network (DNN)-based methods for comparison. Using a newly released dataset of fingering annotations, we conduct systematic evaluations of these models as well as a representative constraint-based method. We find that the methods based on high-order HMMs outperform the other methods in terms of estimation accuracies. We also quantitatively study individual difference of fingering and propose evaluation measures that can be used with multiple ground truth data. We conclude that the HMM-based methods are currently state of the art and generate acceptable fingerings in most parts and that they have certain limitations such as ignorance of phrase boundaries and interdependence of the two hands.

[Retracted] Music Online Education Reform and Wireless Network Optimization Using Artificial Intelligence Piano Teaching

“…MIDI keyboard generates note files with high time resolution, so some notes do not need to be displayed in special positions. The MIDI file of notes must be quantified before attribute extraction to make the generation time and duration of notes appear at the correct rhythm and be quantified [18,19]. Figure 1 displays the dataset quantization process.…”

Score difficulty analysis for piano performance education based on fingering

“…In contrast, in the present research, we explore features related to the piano playing technique. Another work targeting piano difficulty is proposed by Nakamura et al [11,12] and deals with fingering frequencies and playing rate. The rationale for this proposal is that piano fingerings which occur less often, lead to increased difficulty.…”

“…This task is related to piano technique and a proxy to modelling the difficulty of playing a score. The current approaches in piano fingering go from expert systems [18] to local search algorithms [19,20] and, more recently, data-driven methods [11,12]. Towards modelling difficulty, we derive piano technique features from two piano fingering approaches, a knowledge-driven system, Pianoplayer [20], and a data-driven system proposed by Nakamura et al [12].…”

“…1. An example of piano fingering computed for a score (top) with Pianoplayer and Nakamura et al [12] for which we derive the features P-F, P-V, N-F, N-P, and then the corresponding matrices X f (bottom).…”

Analysis of the Usefulness of Critique Documents on Musical Performance: Toward a Better Instructional Document Format

“…Several public datasets or digital archives have been constructed as knowledge resources for music with various perspectives [24], (e.g., performance recordings data [10], metadata [genre, composer, lyrics, etc. [11,27,30]], musical scores [MIDI [16], piano notation [8,31]], information associated with [fingering [22], music analysis [12]], other multimodal information [18,33], emotions [3,35], listening history [26], and performers' interpretations [14,15,21,25]). Most of the datasets are the data of the sound source itself.…”