Toward Faultless Content-Based Playlists Generation for Instrumentals

TL;DR

This paper proposes improved autotagging methods for content-based playlist generation focusing on Songs and Instrumentals, achieving significantly fewer false positives and providing a framework for future research.

Contribution

It introduces novel autotagging enhancements for Songs and Instrumentals, addressing cold start and bias issues, and offers a comprehensive experimental framework and source code for reproducibility.

Findings

Instrumental playlists with up to three times fewer false positives

Enhanced autotagging accuracy for Songs and Instrumentals

Framework for future musical tag research

Abstract

This study deals with content-based musical playlists generation focused on Songs and Instrumentals. Automatic playlist generation relies on collaborative filtering and autotagging algorithms. Autotagging can solve the cold start issue and popularity bias that are critical in music recommender systems. However, autotagging remains to be improved and cannot generate satisfying music playlists. In this paper, we suggest improvements toward better autotagging-generated playlists compared to state-of-the-art. To assess our method, we focus on the Song and Instrumental tags. Song and Instrumental are two objective and opposite tags that are under-studied compared to genres or moods, which are subjective and multi-modal tags. In this paper, we consider an industrial real-world musical database that is unevenly distributed between Songs and Instrumentals and bigger than databases used in previous studies. We set up three incremental experiments to enhance automatic playlist generation. Our suggested approach generates an Instrumental playlist with up to three times less false positives than cutting edge methods. Moreover, we provide a design of experiment framework to foster research on Songs and Instrumentals. We give insight on how to improve further the quality of generated playlists and to extend our methods to other musical tags. Furthermore, we provide the source code to guarantee reproducible research.