Track Role Prediction of Single-Instrumental Sequences

TL;DR

This paper presents a deep learning model that automatically predicts track-roles for single-instrumental music sequences, significantly aiding music composition and analysis by reducing manual effort.

Contribution

The study introduces a novel deep learning approach for automatic track-role prediction in single-instrumental sequences, achieving high accuracy in both symbolic and audio domains.

Findings

87% accuracy in symbolic domain

84% accuracy in audio domain

Potential for AI music generation and analysis

Abstract

In the composition process, selecting appropriate single-instrumental music sequences and assigning their track-role is an indispensable task. However, manually determining the track-role for a myriad of music samples can be time-consuming and labor-intensive. This study introduces a deep learning model designed to automatically predict the track-role of single-instrumental music sequences. Our evaluations show a prediction accuracy of 87% in the symbolic domain and 84% in the audio domain. The proposed track-role prediction methods hold promise for future applications in AI music generation and analysis.