The Effect of Explicit Structure Encoding of Deep Neural Networks for Symbolic Music Generation

by   Ke Chen, et al.

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.


page 4

page 6


Explicitly Conditioned Melody Generation: A Case Study with Interdependent RNNs

Deep generative models for symbolic music are typically designed to mode...

Music Generation with Temporal Structure Augmentation

In this paper we introduce a novel feature augmentation approach for gen...

Psychological constraints on string-based methods for pattern discovery in polyphonic corpora

Researchers often divide symbolic music corpora into contiguous sequence...

JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models

Music generation has attracted growing interest with the advancement of ...

SDMuse: Stochastic Differential Music Editing and Generation via Hybrid Representation

While deep generative models have empowered music generation, it remains...

Symbolic Music Representations for Classification Tasks: A Systematic Evaluation

Music Information Retrieval (MIR) has seen a recent surge in deep learni...

Melodic Phrase Segmentation By Deep Neural Networks

Automated melodic phrase detection and segmentation is a classical task ...

Please sign up or login with your details

Forgot password? Click here to reset