# A Hierarchical Recurrent Neural Network for Symbolic Melody Generation

arXiv: https://arxiv.org/abs/1712.05274 · HTML: https://mlsanity.com/paper/1712.05274/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2017.

## Built on by (most cited first, 14 of 14)

- [Hierarchical Recurrent Neural Networks for Conditional Melody Generation with Long-term Structure](https://mlsanity.com/paper/2102.09794/) (2021)
- [MelodyGLM: Multi-task Pre-training for Symbolic Melody Generation](https://mlsanity.com/paper/2309.10738/) (2023)
- [SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition](https://mlsanity.com/paper/2402.17645/) (2024)
- [A Comprehensive Survey for Evaluation Methodologies of AI-Generated Music](https://mlsanity.com/paper/2308.13736/) (2023)
- [Motifs, Phrases, and Beyond: The Modelling of Structure in Symbolic Music Generation](https://mlsanity.com/paper/2403.07995/) (2024)
- [Generative AI Agents in Autonomous Machines: A Safety Perspective](https://mlsanity.com/paper/2410.15489/) (2024)
- [MeloForm: Generating Melody with Musical Form based on Expert Systems and Neural Networks](https://mlsanity.com/paper/2208.14345/) (2022)
- [WuYun: Exploring hierarchical skeleton-guided melody generation using knowledge-enhanced deep learning](https://mlsanity.com/paper/2301.04488/) (2023)
- [A-Muze-Net: Music Generation by Composing the Harmony based on the Generated Melody](https://mlsanity.com/paper/2111.12986/) (2021)
- [BumbleBee: A Transformer for Music](https://mlsanity.com/paper/2107.03443/) (2021)
- [ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis](https://mlsanity.com/paper/2510.10249/) (2025)
- [A Combination of Multi-Objective Genetic Algorithm and Deep Learning for Music Harmony Generation](https://mlsanity.com/paper/2102.07960/) (2021)
- [Pathway to Future Symbiotic Creativity](https://mlsanity.com/paper/2209.02388/) (2022)
- [AutoSchA: Automatic Hierarchical Music Representations via Multi-Relational Node Isolation](https://mlsanity.com/paper/2512.18232/) (2025)

## Abstract (arXiv)

In recent years, neural networks have been used to generate symbolic melodies. However, the long-term structure in the melody has posed great difficulty for designing a good model. In this paper, we present a hierarchical recurrent neural network for melody generation, which consists of three Long-Short-Term-Memory (LSTM) subnetworks working in a coarse-to-fine manner along time. Specifically, the three subnetworks generate bar profiles, beat profiles and notes in turn, and the output of the high-level subnetworks are fed into the low-level subnetworks, serving as guidance for generating the finer time-scale melody components in low-level subnetworks. Two human behavior experiments demonstrate the advantage of this structure over the single-layer LSTM which attempts to learn all hidden structures in melodies. Compared with the state-of-the-art models MidiNet and MusicVAE, the hierarchical recurrent neural network produces better melodies evaluated by humans.