Do Music Foundation Models Embed Pitch in Helical Structure?

2026-07-31

AI Summary

This study investigates how music foundation models encode pitch information in their internal representations, with a particular focus on whether octave periodicity is inherently captured. By feeding isolated musical notes into pretrained models and employing principal component analysis, visualization of intermediate representations, and cross-model comparisons, the work provides the first empirical evidence that pitch is embedded within these models as a spiral geometric structure. The research further demonstrates that the clarity and morphology of this spiral are influenced by both model architecture and the acoustic characteristics of the input audio. These findings offer novel insights into the representational mechanisms underlying music foundation models and advance our understanding of how fundamental musical attributes are structured in deep neural networks.

Abstract

This study analyzes the intermediate representations of music foundation models (MFMs) and reports the geometric structures used to represent pitch information. By inputting isolated musical notes into trained MFMs and analyzing their principal components, we reveal that the representations form a helical structure reflecting the octave periodicity of pitch. Furthermore, we show that the clarity and geometry of this helical structure vary not only across models but also with the acoustic properties of the input signals. Our analysis provides a novel approach for clarifying the internal mechanisms of MFMs.

Problem

• music foundation models
• pitch representation
• helical structure
• octave periodicity
• intermediate representations

Innovation

• music foundation models
• pitch representation
• helical structure
• octave periodicity
• intermediate representations