Between the AI and Me: Analysing Listeners' Perspectives on AI- and Human-Composed Progressive Metal Music

TL;DR

This study investigates how listeners perceive AI- versus human-created progressive metal music, revealing that while AI can produce genre-specific music, listeners generally prefer human compositions and can distinguish between them.

Contribution

It introduces a mixed methods approach to evaluate listener perceptions of AI-generated music and demonstrates the effectiveness of fine-tuning AI models for genre-specific music generation.

Findings

Listeners can distinguish AI from human music in progressive metal.

Listeners prefer human compositions over AI-generated ones.

Fine-tuning improves AI genre-specific music generation.

Abstract

Generative AI models have recently blossomed, significantly impacting artistic and musical traditions. Research investigating how humans interact with and deem these models is therefore crucial. Through a listening and reflection study, we explore participants' perspectives on AI- vs human-generated progressive metal, in symbolic format, using rock music as a control group. AI-generated examples were produced by ProgGP, a Transformer-based model. We propose a mixed methods approach to assess the effects of generation type (human vs. AI), genre (progressive metal vs. rock), and curation process (random vs. cherry-picked). This combines quantitative feedback on genre congruence, preference, creativity, consistency, playability, humanness, and repeatability, and qualitative feedback to provide insights into listeners' experiences. A total of 32 progressive metal fans completed the study. Our findings validate the use of fine-tuning to achieve genre-specific specialization in AI music generation, as listeners could distinguish between AI-generated rock and progressive metal. Despite some AI-generated excerpts receiving similar ratings to human music, listeners exhibited a preference for human compositions. Thematic analysis identified key features for genre and AI vs. human distinctions. Finally, we consider the ethical implications of our work in promoting musical data diversity within MIR research by focusing on an under-explored genre.