The Effect Of Explicit Structure Encoding Of Deep Neural Networks For Symbolic Music Generation
2018 · Ke Chen, Weilin Zhang, Shlomo Dubnov, et al.
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
Authors
(none)
Tags
Stats
Related papers
- Fusing Memory And Attention: A Study On LSTM, Transformer And Hybrid Architectures For Symbolic Music Generation (2026)0.00
- Rethinking Recurrent Latent Variable Model For Music Composition (2018)7.50
- Midi-sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN Networks For Symbolic Single-track Music Generation (2019)0.00
- Chord Generation From Symbolic Melody Using BLSTM Networks (2017)0.00
- Generating Lead Sheets With Affect: A Novel Conditional Seq2seq Framework (2021)8.60
- Amadeus: Autoregressive Model With Bidirectional Attribute Modelling For Symbolic Music (2025)0.00
- Polyphonic Music Generation With Sequence Generative Adversarial Networks (2017)2.26
- Exploring Single-song Autoencoding Schemes For Audio-based Music Structure Analysis (2021)0.00