Wavelet-Filtering of Symbolic Music Representations for Folk Tune Segmentation and Classification

TL;DR

This paper evaluates a Haar-wavelet filtering method for segmenting and classifying folk tune melodies from symbolic representations, showing improved accuracy over a Gestalt-based approach.

Contribution

It introduces a wavelet-based technique for folk tune segmentation and classification, outperforming previous Gestalt-based methods in accuracy.

Findings

Wavelet filtering improves segmentation accuracy.

Optimized parameters enhance classification performance.

Wavelet-based approach outperforms Gestalt method.

Abstract

The aim of this study is to evaluate a machine-learning method in which symbolic representations of folk songs are segmented and classified into tune families with Haar-wavelet filtering. The method is compared with previously proposed Gestalt-based method. Melodies are represented as discrete symbolic pitch-time signals. We apply the continuous wavelet transform (CWT) with the Haar wavelet at specific scales, obtaining filtered versions of melodies emphasizing their information at particular time-scales. We use the filtered signal for representation and segmentation, using the wavelet coefficients' local maxima to indicate local boundaries and classify segments by means of k-nearest neighbours based on standard vector-metrics (Euclidean, cityblock), and compare the results to a Gestalt-based segmentation method and metrics applied directly to the pitch signal. We found that the wavelet based segmentation and wavelet-filtering of the pitch signal lead to better classification accuracy in cross-validated evaluation when the time-scale and other parameters are optimized.