# Ensemble-based cover song detection

## TL;DR

This paper presents an ensemble-based approach for cover song detection that considers multiple tracks simultaneously, leveraging relationships between versions to improve accuracy at scale.

## Contribution

It introduces a novel many-to-many ensemble method that constructs and exploits a graph of track relationships, enhancing detection performance over pairwise methods.

## Key findings

- Significant performance improvement with large sets of versions
- Effective use of track relationship graphs
- Better scalability for industrial applications

## Abstract

Audio-based cover song detection has received much attention in the MIR community in the recent years. To date, the most popular formulation of the problem has been to compare the audio signals of two tracks and to make a binary decision based on this information only. However, leveraging additional signals might be key if one wants to solve the problem at an industrial scale. In this paper, we introduce an ensemble-based method that approaches the problem from a many-to-many perspective. Instead of considering pairs of tracks in isolation, we consider larger sets of potential versions for a given composition, and create and exploit the graph of relationships between these tracks. We show that this can result in a significant improvement in performance, in particular when the number of existing versions of a given composition is large.