LyCon: Lyrics Reconstruction from the Bag-of-Words Using Large Language Models

TL;DR

This paper presents LyCon, a method that uses large language models and metadata to reconstruct copyright-free lyrics from Bag-of-Words datasets, enabling lyric research without copyright issues.

Contribution

The study introduces a novel approach for generating lyrics from BoW datasets using metadata and large language models, and provides a publicly available dataset of reconstructed lyrics.

Findings

Successfully reconstructed lyrics aligned with metadata

Created a publicly accessible dataset of reconstructed lyrics

Enabled new research possibilities in lyric studies

Abstract

This paper addresses the unique challenge of conducting research in lyric studies, where direct use of lyrics is often restricted due to copyright concerns. Unlike typical data, internet-sourced lyrics are frequently protected under copyright law, necessitating alternative approaches. Our study introduces a novel method for generating copyright-free lyrics from publicly available Bag-of-Words (BoW) datasets, which contain the vocabulary of lyrics but not the lyrics themselves. Utilizing metadata associated with BoW datasets and large language models, we successfully reconstructed lyrics. We have compiled and made available a dataset of reconstructed lyrics, LyCon, aligned with metadata from renowned sources including the Million Song Dataset, Deezer Mood Detection Dataset, and AllMusic Genre Dataset, available for public access. We believe that the integration of metadata such as mood annotations or genres enables a variety of academic experiments on lyrics, such as conditional lyric generation.