Leveraging User-Generated Metadata of Online Videos for Cover Song Identification

TL;DR

This paper presents a multi-modal approach that combines user-generated metadata and audio content to improve cover song identification on YouTube, demonstrating that metadata can enhance the stability and accuracy of retrieval.

Contribution

It introduces a novel multi-modal method integrating metadata and audio content for cover song identification, which is a significant advancement over audio-only approaches.

Findings

Metadata improves identification stability

Multi-modal approach outperforms audio-only methods

Metadata integration enhances retrieval accuracy

Abstract

YouTube is a rich source of cover songs. Since the platform itself is organized in terms of videos rather than songs, the retrieval of covers is not trivial. The field of cover song identification addresses this problem and provides approaches that usually rely on audio content. However, including the user-generated video metadata available on YouTube promises improved identification results. In this paper, we propose a multi-modal approach for cover song identification on online video platforms. We combine the entity resolution models with audio-based approaches using a ranking model. Our findings implicate that leveraging user-generated metadata can stabilize cover song identification performance on YouTube.