# Melody Harmonization Using Orderless NADE, Chord Balancing, and Blocked Gibbs Sampling

arXiv: https://arxiv.org/abs/2010.13468 · HTML: https://mlsanity.com/paper/2010.13468/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [Emotion-Driven Melody Harmonization via Melodic Variation and Functional Representation](https://mlsanity.com/paper/2407.20176/) (2024)
- [A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectives](https://mlsanity.com/paper/2210.13944/) (2022)
- [Choir Transformer: Generating Polyphonic Music with Relative Attention on Transformer](https://mlsanity.com/paper/2308.02531/) (2023)
- [Emotion-Conditioned Melody Harmonization with Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2306.03718/) (2023)
- [Incorporating Structure and Chord Constraints in Symbolic Transformer-based Melodic Harmonization](https://mlsanity.com/paper/2512.07627/) (2025)
- [AI Harmonizer: Expanding Vocal Expression with a Generative Neurosymbolic Music AI System](https://mlsanity.com/paper/2506.18143/) (2025)
- [Pay (Cross) Attention to the Melody: Curriculum Masking for Single-Encoder Melodic Harmonization](https://mlsanity.com/paper/2601.16150/) (2026)

## Abstract (arXiv)

Coherence and interestingness are two criteria for evaluating the performance of melody harmonization, which aims to generate a chord progression from a symbolic melody. In this study, we apply the concept of orderless NADE, which takes the melody and its partially masked chord sequence as the input of the BiLSTM-based networks to learn the masked ground truth, to the training process. In addition, the class weights are used to compensate for some reasonable chord labels that are rarely seen in the training set. Consistent with the stochasticity in training, blocked Gibbs sampling with proper numbers of masking/generating loops is used in the inference phase to progressively trade the coherence of the generated chord sequence off against its interestingness. The experiments were conducted on a dataset of 18,005 melody/chord pairs. Our proposed model outperforms the state-of-the-art system MTHarmonizer in five of six different objective metrics based on chord/melody harmonicity and chord progression. The subjective test results with more than 100 participants also show the superiority of our model.