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

The surprisingness of a song is an essential and seemingly subjective factorin determining whether the listener likes it. With the help of informationtheory, it can be described as the transition probability of a music sequencemodeled as a Markov chain. In this study, we introduce the concept of derivingentropy variations over time, so that the surprise contour of each chordsequence can be extracted. Based on this, we propose a user-controllableframework that uses a conditional variational autoencoder (CVAE) to harmonizethe melody based on the given chord surprise indication. Through explicitconditions, the model can randomly generate various and harmonic chordprogressions for a melody, and the Spearman's correlation and p-valuesignificance show that the resulting chord progressions match the givensurprise contour quite well. The vanilla CVAE model was evaluated in a basicmelody harmonization task (no surprise control) in terms of six objectivemetrics. The results of experiments on the Hooktheory Lead Sheet Dataset showthat our model achieves performance comparable to the state-of-the-art melodyharmonization model.

SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours