English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Most existing neural network models for music generation explore how togenerate music bars, then directly splice the music bars into a song. However,these methods do not explore the relationship between the bars, and theconnected song as a whole has no musical form structure and sense of musicaldirection. To address this issue, we propose a Multi-model Multi-taskHierarchical Conditional VAE-GAN (Variational Autoencoder-Generativeadversarial networks) networks, named MIDI-Sandwich, which combines musicalknowledge, such as musical form, tonic, and melodic motion. The MIDI-Sandwichhas two submodels: Hierarchical Conditional Variational Autoencoder (HCVAE) andHierarchical Conditional Generative Adversarial Network (HCGAN). The HCVAE useshierarchical structure. The underlying layer of HCVAE uses Local ConditionalVariational Autoencoder (L-CVAE) to generate a music bar which is pre-specifiedby the First and Last Notes (FLN). The upper layer of HCVAE uses GlobalVariational Autoencoder(G-VAE) to analyze the latent vector sequence generatedby the L-CVAE encoder, to explore the musical relationship between the bars,and to produce the song pieced together by multiple music bars generated by theL-CVAE decoder, which makes the song both have musical structure and sense ofdirection. At the same time, the HCVAE shares a part of itself with the HCGANto further improve the performance of the generated music. The MIDI-Sandwich isvalidated on the Nottingham dataset and is able to generate a single-trackmelody sequence (17x8 beats), which is superior to the length of most of thegenerated models (8 to 32 beats). Meanwhile, by referring to the experimentalmethods of many classical kinds of literature, the quality evaluation of thegenerated music is performed. The above experiments prove the validity of themodel.

MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation