Identifying Metric Types with Optimized DFT and Autocorrelation Models

被引：0

作者：

Chiu, Matt ^{[1
]}

Yust, Jason ^{[2
]}

机构：

[1] Eastman Sch Mus, Rochester, NY 14604 USA

[2] Boston Univ, Boston, MA 02215 USA

来源：

MATHEMATICS AND COMPUTATION IN MUSIC (MCM 2022) | 2022年

关键词：

Discrete Fourier transform; Autocorrelation; Meter classification; Metric types; Neural networks; METER;

D O I：

10.1007/978-3-031-07015-0_28

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This paper explores the classification of metric types using different feature representations. Using weighted timepoint, DFT, and autocorrelation, we train feedforward neural networks to distinguish allemandes, courantes, sarabandes, and gavottes in the Yale-Classical Archives Corpus. Autocorrelation and DFT models perform better than a baseline, with DFT consistently better by a small amount.

引用

页码：343 / 348

页数：6

共 19 条

[1] Agarap A. F., 2018, arXiv, DOI [10.48550/arXiv.1803.08375, DOI 10.48550/ARXIV.1803.08375]
[2] Amiot E., 2016, MUSIC FOURIER SPACE, DOI [10.1007/978-3-319-45581-5, DOI 10.1007/978-3-319-45581-5]
[3] DETERMINATION OF THE METER OF MUSICAL SCORES BY AUTOCORRELATION
BROWN, JC
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1993, 94 (04) : 1953 - 1957
[4] Chiu M., 2018, THESIS BOSTON U
[5] Prefatory Note: How Music Theorists Model Time
Cohn, Richard
[J]. JOURNAL OF MUSIC THEORY, 2021, 65 (01) : 11 - 38
[6] Identifying metrical and temporal structure with an autocorrelation phase matrix
Eck, Douglas
[J]. MUSIC PERCEPTION, 2006, 24 (02): : 167 - 176
[7] Eerola T., 2004, MIDI TOOLBOX MATLAB
[8] Flannick J.E., 2005, RENAISSANCE BANFF MA, P195
[9] Kingma DP, 2014, ADV NEUR IN, V27
[10] Lerdahl Fred., 1983, GENERATIVE THEORY TO

← 1 2 →