AI harmonization matches melody but misses human story elements
From Human Narrative to Harmonic Structure: A Human-Centered Investigation of Algorithmic Music Generation through the Chord Wheel Diagram
Artificial IntelligenceSound
Summary
This paper looks at how AI can create music harmonies that fit a melody but don’t always capture the original human choices that reflect personal or cultural stories. By comparing famous songs by Bob Dylan and others with AI-generated harmonies, the researchers found that AI can follow musical rules but often changes the unique patterns that humans use to tell stories with chords. The study suggests machines making music should consider not just rules but also the story and intention behind the music.
What this means in practice
- •For automated music producers: Enhance AI tools to generate harmonies that better preserve human compositional intent and narrative structure beyond just harmonic correctness.
- •For music software developers: Design music editing software that visually represents and compares human and AI harmonic decisions to assist musicians in creative choices.
Authors
Josef Pavlíček, Petra Pavlíčková, Irena Štrausová
Abstract
Contemporary AI-based music generation can produce compositions that satisfy formal requirements of tonality and musical coherence. However, whether musical expression can be described by mathematical properties alone remains a fundamental question. Human composers operate within personal and cultural contexts that influence harmonic decisions and deliberate departures from established patterns. This study investigates six narrative-driven popular songs by Bob Dylan, Johnny Cash, and Ritchie Valens. Original human harmonies are compared with outputs of an explainable computational harmonizer operating on the same melodies without access to the original chord progressions. We examine harmonic vocabulary, functional persistence, repetition, non-diatonic events, and tension-resolution patterns using Chord Wheel Diagrams and BPMN-based representations. Results show that high melody-chord compatibility does not necessarily imply preservation of the original human harmonic decision pattern. Some generated harmonizations retain the economical structure of the reference, while others alter harmonic diversity or suppress distinctive events while remaining compatible with the melody. Rather than quantifying artistic quality, the study introduces narrative-conditioned harmonic structure as a complementary perspective for computational music analysis. The findings suggest that generative systems may benefit from modeling not only harmonic correctness, but also structural identity, context, and human compositional intention.