A Hierarchical Recurrent Neural Network for Symbolic Melody Generation
arXiv:1712.05274
Abstract
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.
arXiv comment9 pages
References in corpus (10)
- WaveNet: A Generative Model for Raw Audio
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
- SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
- A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
- MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
- A Clockwork RNN
- A Hierarchical Neural Autoencoder for Paragraphs and Documents
- MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
- Algorithmic Composition of Melodies with Deep Recurrent Neural Networks