Insights on Harmonic Tones from a Generative Music Experiment
For music AI researchers and cognitive scientists, this provides empirical evidence that generative AI can produce complex harmonic structures, offering insights into human pitch perception.
In a studio-lab experiment with music producers and a generative AI model for bass-like audio, producers used the model's output to convey multiple pitches with single harmonic complex tones, revealing the model learned to generate structured simultaneous melodic lines monophonically. This challenges the debate on human perception of harmonics as distinct pitches.
The ultimate purpose of generative music AI is music production. The studio-lab, a social form within the art-science branch of cross-disciplinarity, is a way to advance music production with AI music models. During a studio-lab experiment involving researchers, music producers, and an AI model for music generating bass-like audio, it was observed that the producers used the model's output to convey two or more pitches with a single harmonic complex tone, which in turn revealed that the model had learned to generate structured and coherent simultaneous melodic lines using monophonic sequences of harmonic complex tones. These findings prompt a reconsideration of the long-standing debate on whether humans can perceive harmonics as distinct pitches and highlight how generative AI can not only enhance musical creativity but also contribute to a deeper understanding of music.