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

Currently, almost all the multi-track music generation models use theConvolutional Neural Network (CNN) to build the generative model, while theRecurrent Neural Network (RNN) based models can not be applied in this task. Inview of the above problem, this paper proposes a RNN-based HierarchicalMulti-modal Fusion Generation Variational Autoencoder (VAE) network,MIDI-Sandwich2, for multi-track symbolic music generation. Inspired by VQ-VAE2,MIDI-Sandwich2 expands the dimension of the original hierarchical model byusing multiple independent Binary Variational Autoencoder (BVAE) models withoutsharing weights to process the information of each track. Then, withmulti-modal fusion technology, the upper layer named Multi-modal FusionGeneration VAE (MFG-VAE) combines the latent space vectors generated by therespective tracks, and uses the decoder to perform the ascending dimensionreconstruction to simulate the inverse operation of multi-modal fusion,multi-modal generation, so as to realize the RNN-based multi-track symbolicmusic generation. For the multi-track format pianoroll, we also improve theoutput binarization method of MuseGAN, which solves the problem that therefinement step of the original scheme is difficult to differentiate and thegradient is hard to descent, making the generated song more expressive. Themodel is validated on the Lakh Pianoroll Dataset (LPD) multi-track dataset.Compared to the MuseGAN, MIDI-Sandwich2 can not only generate harmoniousmulti-track music, the generation quality is also close to the state of the artlevel. At the same time, by using the VAE to restore songs, the semi-generatedsongs reproduced by the MIDI-Sandwich2 are more beautiful than the pureautogeneration music generated by MuseGAN. Both the code and the audition audiosamples are open source on https://github.com/LiangHsia/MIDI-S2.

MIDI-Sandwich2: RNN-based Hierarchical Multi-modal Fusion Generation VAE networks for multi-track symbolic music generation