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

We are interested in the task of generating multi-instrumental music scores.The Transformer architecture has recently shown great promise for the task ofpiano score generation; here we adapt it to the multi-instrumental setting.Transformers are complex, high-dimensional language models which are capable ofcapturing long-term structure in sequence data, but require large amounts ofdata to fit. Their success on piano score generation is partially explained bythe large volumes of symbolic data readily available for that domain. Weleverage the recently-introduced NES-MDB dataset of four-instrument scores froman early video game sound synthesis chip (the NES), which we find to bewell-suited to training with the Transformer architecture. To further improvethe performance of our model, we propose a pre-training technique to leveragethe information in a large collection of heterogeneous music, namely the LakhMIDI dataset. Despite differences between the two corpora, we find that thistransfer learning procedure improves both quantitative and qualitativeperformance for our primary task.

LakhNES: Improving multi-instrumental music generation with cross-domain pre-training