A Convolutional Approach to Melody Line Identification in Symbolic Scores

TL;DR

This paper introduces a CNN-based method for automatically identifying the main melody line in symbolic musical scores, aiding musicological analysis and retrieval without audio playback.

Contribution

It presents a novel convolutional neural network approach for melody line detection in symbolic scores, including a method for analyzing note influence on predictions.

Findings

Effective melody identification demonstrated on multiple datasets

The CNN accurately predicts melody notes with high precision

Analysis method reveals note influence patterns in predictions

Abstract

In many musical traditions, the melody line is of primary significance in a piece. Human listeners can readily distinguish melodies from accompaniment; however, making this distinction given only the written score -- i.e. without listening to the music performed -- can be a difficult task. Solving this task is of great importance for both Music Information Retrieval and musicological applications. In this paper, we propose an automated approach to identifying the most salient melody line in a symbolic score. The backbone of the method consists of a convolutional neural network (CNN) estimating the probability that each note in the score (more precisely: each pixel in a piano roll encoding of the score) belongs to the melody line. We train and evaluate the method on various datasets, using manual annotations where available and solo instrument parts where not. We also propose a method to inspect the CNN and to analyze the influence exerted by notes on the prediction of other notes; this method can be applied whenever the output of a neural network has the same size as the input.