Abusive music and song transformation using GenAI and LLMs

TL;DR

This paper investigates how GenAI and LLMs can transform abusive lyrics and vocal tones in music to reduce aggression and harmful content while maintaining musical coherence, offering a new approach to content moderation.

Contribution

It introduces a novel method for transforming abusive music content using GenAI, focusing on tone and sentiment rather than simple censorship, and provides a comparative analysis of its effectiveness.

Findings

Significant reduction in vocal aggressiveness and harmful sentiment.

Improved acoustic quality metrics such as Harmonic to Noise Ratio.

Maintained musical coherence after transformation.

Abstract

Repeated exposure to violence and abusive content in music and song content can influence listeners' emotions and behaviours, potentially normalising aggression or reinforcing harmful stereotypes. In this study, we explore the use of generative artificial intelligence (GenAI) and Large Language Models (LLMs) to automatically transform abusive words (vocal delivery) and lyrical content in popular music. Rather than simply muting or replacing a single word, our approach transforms the tone, intensity, and sentiment, thus not altering just the lyrics, but how it is expressed. We present a comparative analysis of four selected English songs and their transformed counterparts, evaluating changes through both acoustic and sentiment-based lenses. Our findings indicate that Gen-AI significantly reduces vocal aggressiveness, with acoustic analysis showing improvements in Harmonic to Noise Ratio, Cepstral Peak Prominence, and Shimmer. Sentiment analysis reduced aggression by 63.3-85.6\% across artists, with major improvements in chorus sections (up to 88.6\% reduction). The transformed versions maintained musical coherence while mitigating harmful content, offering a promising alternative to traditional content moderation that avoids triggering the "forbidden fruit" effect, where the censored content becomes more appealing simply because it is restricted. This approach demonstrates the potential for GenAI to create safer listening experiences while preserving artistic expression.