Synthetic Lyrics Detection Across Languages and Genres

TL;DR

This paper investigates the detection of AI-generated lyrics across multiple languages and genres, creating a diverse dataset and evaluating detection methods to improve transparency and address copyright concerns.

Contribution

It introduces a new dataset of real and synthetic lyrics across languages and genres, and evaluates and adapts detection methods for lyrics, a previously unexplored domain.

Findings

Detection methods show promising results across languages and genres.

Unsupervised domain adaptation improves detection accuracy.

Methods generalize well with limited data in few-shot scenarios.

Abstract

In recent years, the use of large language models (LLMs) to generate music content, particularly lyrics, has gained in popularity. These advances provide valuable tools for artists and enhance their creative processes, but they also raise concerns about copyright violations, consumer satisfaction, and content spamming. Previous research has explored content detection in various domains. However, no work has focused on the text modality, lyrics, in music. To address this gap, we curated a diverse dataset of real and synthetic lyrics from multiple languages, music genres, and artists. The generation pipeline was validated using both humans and automated methods. We performed a thorough evaluation of existing synthetic text detection approaches on lyrics, a previously unexplored data type. We also investigated methods to adapt the best-performing features to lyrics through unsupervised domain adaptation. Following both music and industrial constraints, we examined how well these approaches generalize across languages, scale with data availability, handle multilingual language content, and perform on novel genres in few-shot settings. Our findings show promising results that could inform policy decisions around AI-generated music and enhance transparency for users.