# Dissonance Spectrum explicitly models perceptual frequency interactions for better music understanding

arXiv: https://arxiv.org/abs/2608.25621 · HTML: https://mlsanity.com/paper/2608.25621/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 41 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://mlsanity.com/paper/2306.00107/) (2023)
- [Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning](https://mlsanity.com/paper/2308.11276/) (2023)
- [A Foundation Model for Music Informatics](https://mlsanity.com/paper/2311.03318/) (2023)
- [MusiLingo: Bridging Music and Text with Pre-trained Language Models for Music Captioning and Query Response](https://mlsanity.com/paper/2309.08730/) (2023)
- [SpecTNT: a Time-Frequency Transformer for Music Audio](https://mlsanity.com/paper/2110.09127/) (2021)
- [Towards Explainable Music Emotion Recognition: The Route via Mid-level Features](https://mlsanity.com/paper/1907.03572/) (2019)
- [Feature Learning for Chord Recognition: The Deep Chroma Extractor](https://mlsanity.com/paper/1612.05065/) (2016)
- [Towards Unified Music Emotion Recognition across Dimensional and Categorical Models](https://mlsanity.com/paper/2502.03979/) (2025)
- [Harmony Perception by Periodicity Detection](https://mlsanity.com/paper/1306.6458/) (2013)
- [From Discord to Harmony: Decomposed Consonance-based Training for Improved Audio Chord Estimation](https://mlsanity.com/paper/2509.01588/) (2025)
- [Psychoacoustic study of simple-tone dyads: frequency ratio and pitch](https://mlsanity.com/paper/2510.01201/) (2025)

## Abstract (arXiv)

Conventional music representations describe acoustic energy over time and frequency but do not explicitly expose relations among simultaneous frequency components. We introduce the Dissonance Spectrum (DS), a nonnegative time--frequency representation that applies a tolerance-based rational pitch-relation kernel with logarithmic harmonic distance to a constant-Q spectrum and attributes aggregate pairwise interactions back to individual frequency bins. Controlled music-theory tests show strong ordinal agreement for intervals, harmonic-function connections, and church modes, and weaker but significant agreement across diverse chord voicings. DS is then encoded by a lightweight parallel branch whose zero-initialized residual projection preserves the baseline function at initialization. Across six paired training seeds in open-ended music question answering and categorical and dimensional music emotion recognition, DS obtains the highest mean on every reported endpoint relative to the unchanged baseline, a parameter-matched Gaussian-input branch, and an architecture-matched magnitude-CQT branch. These results support DS as an interpretable, complementary representation, while listener-specific perception and broader task coverage remain open problems.