Finding Tori: Self-supervised Learning for Analyzing Korean Folk Song

TL;DR

This paper presents a self-supervised learning approach using CNNs on pitch contours to analyze Korean folk songs, effectively capturing the musical concept of tori and revealing insights into traditional musical classifications.

Contribution

It introduces a novel self-supervised learning method for analyzing folk music recordings, specifically capturing the concept of tori from field recordings.

Findings

Better capture of tori characteristics than traditional methods

Demonstrated the effectiveness of CNNs on pitch contours

Provided insights into Korean folk music classifications

Abstract

In this paper, we introduce a computational analysis of the field recording dataset of approximately 700 hours of Korean folk songs, which were recorded around 1980-90s. Because most of the songs were sung by non-expert musicians without accompaniment, the dataset provides several challenges. To address this challenge, we utilized self-supervised learning with convolutional neural network based on pitch contour, then analyzed how the musical concept of tori, a classification system defined by a specific scale, ornamental notes, and an idiomatic melodic contour, is captured by the model. The experimental result shows that our approach can better capture the characteristics of tori compared to traditional pitch histograms. Using our approaches, we have examined how musical discussions proposed in existing academia manifest in the actual field recordings of Korean folk songs.