Claraprint: a chord and melody based fingerprint for western classical music cover detection

TL;DR

This paper introduces Claraprint, a novel fingerprinting method tailored for Western classical music to improve cover song detection, and provides a new dataset to facilitate research in this genre.

Contribution

The paper presents a specialized fingerprinting technique for classical music cover detection and introduces a new dataset to support further research in this area.

Findings

Effective retrieval of cover classical music using Claraprint

New dataset promotes research in classical cover detection

Fingerprint algorithm tailored for classical music characteristics

Abstract

Cover song detection has been an active field in the Music Information Retrieval (MIR) community during the past decades. Most of the research community focused in solving it for a wide range of music genres with diverse characteristics. Western classical music, a genre heavily based on the recording of "cover songs", or musical works, represents a large heritage, offering immediate application for an efficient fingerprint algorithm. We propose an engineering approach for retrieving a cover song from a reference database thanks to a fingerprint designed for classical musical works. We open a new data set to encourage the scientific community to use it for further researches regarding this genre.