<abstract xmlns="http://www.w3.org/1999/xhtml">
<p>The current hotspots of empirical analysis of piano performance skills mainly focus on the recognition of single notes, and there are some limitations in recognition accuracy and noise resistance performance. In this paper, to address this problem, firstly, on the basis of big data, we propose to realize the segmentation of the music section and noise section based on the single-port limit energy difference method and perform note onset and stop detection for the music section based on LMS adaptive filtering algorithm, using the musical characteristics of piano to identify the energy jumping point, which effectively improves the accuracy of note onset and stop detection and avoids the situation of missing and wrong diagnosis. Then the piano piece was played as an example, and the scientific evaluation of the piano performance skills was made based on the results of the determination of note types. The results showed that the errors of the eight notes of the piece were 0.9%, 0.30%, 0.24%, 0.28%, 0.34%, 0.11%, 0.63% and 0.28%. The correct rate of determining the types of notes in the performance technique of the music was 100%, and the error of determining all notes was controlled within 1%. This study provides a reference standard for evaluating the quality of music performance and has broad application prospects in the fields of family leisure, music tutoring, etc.</p>
</abstract>

The current hotspots of empirical analysis of piano performance skills mainly focus on the recognition of single notes, and there are some limitations in recognition accuracy and noise resistance performance. In this paper, to address this problem, firstly, on the basis of big data, we propose to realize the segmentation of the music section and noise section based on the single-port limit energy difference method and perform note onset and stop detection for the music section based on LMS adaptive filtering algorithm, using the musical characteristics of piano to identify the energy jumping point, which effectively improves the accuracy of note onset and stop detection and avoids the situation of missing and wrong diagnosis. Then the piano piece was played as an example, and the scientific evaluation of the piano performance skills was made based on the results of the determination of note types. The results showed that the errors of the eight notes of the piece were 0.9%, 0.30%, 0.24%, 0.28%, 0.34%, 0.11%, 0.63% and 0.28%. The correct rate of determining the types of notes in the performance technique of the music was 100%, and the error of determining all notes was controlled within 1%. This study provides a reference standard for evaluating the quality of music performance and has broad application prospects in the fields of family leisure, music tutoring, etc.

An empirical analysis of the evolution of piano performance skills based on big data

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The current hotspots of empirical analysis of piano performance skills mainly focus on the recognition of single notes, and there are some limitations in...

An empirical analysis of the evolution of piano performance skills based on big data

Online veröffentlicht: 30. Sept. 2023

Seitenbereich: -

Eingereicht: 28. Okt. 2022

Akzeptiert: 10. Apr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00397

Schlüsselwörter
Big data, LMS adaptive filtering algorithm, Musical characteristics, Energy jump point.

© 2023 Yuyu Zhang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

An empirical analysis of the evolution of piano performance skills based on big data

Online veröffentlicht: 30. Sept. 2023

Seitenbereich: -

Eingereicht: 28. Okt. 2022

Akzeptiert: 10. Apr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00397

SchlüsselwörterBig data, LMS adaptive filtering algorithm, Musical characteristics, Energy jump point.

© 2023 Yuyu Zhang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Big data, LMS adaptive filtering algorithm, Musical characteristics, Energy jump point.