Innovations in Cover Song Detection: A Lyrics-Based Approach

TL;DR

This paper presents a novel lyrics-based method for cover song detection, introducing a new dataset with annotated lyrics, and demonstrates improved accuracy over existing approaches.

Contribution

The paper introduces a new lyrics-based approach for cover song detection and provides a comprehensive dataset with annotated lyrics for original and cover songs.

Findings

Our method outperforms baseline approaches in cover song detection accuracy.

The new dataset with annotated lyrics enhances research in cover song identification.

Lyrics-based features are effective for distinguishing cover songs from originals.

Abstract

Cover songs are alternate versions of a song by a different artist. Long being a vital part of the music industry, cover songs significantly influence music culture and are commonly heard in public venues. The rise of online music platforms has further increased their prevalence, often as background music or video soundtracks. While current automatic identification methods serve adequately for original songs, they are less effective with cover songs, primarily because cover versions often significantly deviate from the original compositions. In this paper, we propose a novel method for cover song detection that utilizes the lyrics of a song. We introduce a new dataset for cover songs and their corresponding originals. The dataset contains 5078 cover songs and 2828 original songs. In contrast to other cover song datasets, it contains the annotated lyrics for the original song and the cover song. We evaluate our method on this dataset and compare it with multiple baseline approaches. Our results show that our method outperforms the baseline approaches.