Abusive music and song transformation using GenAI and LLMs

2026-01-21

AI Summary

This study addresses the concern that violent and derogatory content in music may reinforce aggressive behaviors and perpetuate harmful stereotypes. To overcome limitations of conventional censorship methods—such as muting or keyword substitution, which often trigger the “forbidden fruit effect” and compromise artistic integrity—the authors propose a generative AI–based framework that jointly moderates both lyrics and vocal delivery style using large language models. By integrating semantic understanding with acoustic features—including harmonics-to-noise ratio, cepstral peak prominence, and perturbation measures—the approach systematically reduces lyrical aggression and emotional intensity while preserving musical coherence. Experimental results demonstrate a significant reduction in perceived emotional aggressiveness, ranging from 63.3% to 88.6%, with chorus segments showing the highest decrease of 88.6%, thereby enhancing auditory safety without sacrificing artistic expression.

Technology Category

• Natural Language Processing: Safety and Robustness
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• abusive content
• music transformation
• content moderation
• aggressive lyrics
• harmful stereotypes

Innovation

• Generative AI
• Large Language Models
• Abusive Content Transformation
• Sentiment-Aware Audio Processing
• Harmonic-to-Noise Ratio