The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation
arXiv:1811.08380 · doi:10.1109/MMRP.2019.00022
Abstract
With recent breakthroughs in artificial neural networks, deep generative models have become one of the leading techniques for computational creativity. Despite very promising progress on image and short sequence generation, symbolic music generation remains a challenging problem since the structure of compositions are usually complicated. In this study, we attempt to solve the melody generation problem constrained by the given chord progression. This music meta-creation problem can also be incorporated into a plan recognition system with user inputs and predictive structural outputs. In particular, we explore the effect of explicit architectural encoding of musical structure via comparing two sequential generative models: LSTM (a type of RNN) and WaveNet (dilated temporal-CNN). As far as we know, this is the first study of applying WaveNet to symbolic music generation, as well as the first systematic comparison between temporal-CNN and RNN for music generation. We conduct a survey for evaluation in our generations and implemented Variable Markov Oracle in music pattern discovery. Experimental results show that to encode structure more explicitly using a stack of dilated convolution layers improved the performance significantly, and a global encoding of underlying chord progression into the generation procedure gains even more.
arXiv comment8 pages, 13 figures
References in corpus (9)
- WaveNet: A Generative Model for Raw Audio
- A Critical Review of Recurrent Neural Networks for Sequence Learning
- Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
- Parallel WaveNet: Fast High-Fidelity Speech Synthesis
- Counterpoint by Convolution
- Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints
- A Unit Selection Methodology for Music Generation Using Deep Neural Networks
- Neural Style Transfer for Audio Spectograms
- Fast Wavenet Generation Algorithm