Polyphonic Music Generation With Sequence Generative Adversarial Networks

Abstract

We propose an application of sequence generative adversarial networks (SeqGAN), which are generative adversarial networks for discrete sequence generation, for creating polyphonic musical sequences. Instead of a monophonic melody generation suggested in the original work, we present an efficient representation of a polyphony MIDI file that simultaneously captures chords and melodies with dynamic timings. The proposed method condenses duration, octaves, and keys of both melodies and chords into a single word vector representation, and recurrent neural networks learn to predict distributions of sequences from the embedded musical word space. We experiment with the original method and the least squares method to the discriminator, which is known to stabilize the training of GANs. The network can create sequences that are musically coherent and shows an improved quantitative and qualitative measures. We also report that careful optimization of reinforcement learning signals of the model is

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keylee2017polyphonic

Related papers

• Music Generation Based On Generative Adversarial Networks With Transformer (2023)0.00
• 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
• Interpretable Melody Generation From Lyrics With Discrete-valued Adversarial Training (2022)6.34
• Melody-conditioned Lyrics Generation With Seqgans (2020)7.50
• Rethinking Recurrent Latent Variable Model For Music Composition (2018)7.50
• Unconditional Audio Generation With Generative Adversarial Networks And Cycle Regularization (2020)9.41
• Objective-reinforced Generative Adversarial Networks (ORGAN) For Sequence Generation Models (2017)0.00