# Unsupervised Learning of Harmonic Analysis Based on Neural HSMM with Code Quality Templates

arXiv: https://arxiv.org/abs/2403.04135 · HTML: https://mlsanity.com/paper/2403.04135/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 33 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 4 of 4)

- [Discovering Discrete Latent Topics with Neural Variational Inference](https://mlsanity.com/paper/1706.00359/) (2017)
- [Unsupervised Neural Hidden Markov Models](https://mlsanity.com/paper/1609.09007/) (2016)
- [A Tutorial on Deep Latent Variable Models of Natural Language](https://mlsanity.com/paper/1812.06834/) (2018)
- [Chord Recognition in Symbolic Music: A Segmental CRF Model, Segment-Level Features, and Comparative Evaluations on Classical and Popular Music](https://mlsanity.com/paper/1810.10002/) (2018)

## Abstract (arXiv)

This paper presents a method of unsupervised learning of harmonic analysis based on a hidden semi-Markov model (HSMM). We introduce the chord quality templates, which specify the probability of pitch class emissions given a root note and a chord quality. Other probability distributions that comprise the HSMM are automatically learned via unsupervised learning, which has been a challenge in existing research. The results of the harmonic analysis of the proposed model were evaluated using existing labeled data. While our proposed method has yet to perform as well as existing models that used supervised learning and complex rule design, it has the advantage of not requiring expensive labeled data or rule elaboration. Furthermore, we also show how to recognize the tonic without prior knowledge, based on the transition probabilities of the Markov model.