Knowledge-based Multimodal Music Similarity

TL;DR

This paper proposes a fully explainable system for music similarity that integrates symbolic and audio content, enhancing interpretability and user control in music retrieval and analysis.

Contribution

It introduces a novel approach combining symbolic and audio data to improve interpretability in music similarity systems.

Findings

Developed a multimodal similarity model combining symbolic and audio features.

Enhanced interpretability and user control in music similarity assessments.

Improved understanding of musical influences and analogies.

Abstract

Music similarity is an essential aspect of music retrieval, recommendation systems, and music analysis. Moreover, similarity is of vital interest for music experts, as it allows studying analogies and influences among composers and historical periods. Current approaches to musical similarity rely mainly on symbolic content, which can be expensive to produce and is not always readily available. Conversely, approaches using audio signals typically fail to provide any insight about the reasons behind the observed similarity. This research addresses the limitations of current approaches by focusing on the study of musical similarity using both symbolic and audio content. The aim of this research is to develop a fully explainable and interpretable system that can provide end-users with more control and understanding of music similarity and classification systems.