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

Deep generative models for audio synthesis have recently been significantlyimproved. However, the task of modeling raw-waveforms remains a difficultproblem, especially for audio waveforms and music signals. Recently, therealtime audio variational autoencoder (RAVE) method was developed forhigh-quality audio waveform synthesis. The RAVE method is based on thevariational autoencoder and utilizes the two-stage training strategy.Unfortunately, the RAVE model is limited in reproducing wide-pitch polyphonicmusic sound. Therefore, to enhance the reconstruction performance, we adopt thepitch activation data as an auxiliary information to the RAVE model. To handlethe auxiliary information, we propose an enhanced RAVE model with a conditionalvariational autoencoder structure and an additional fully-connected layer. Toevaluate the proposed structure, we conducted a listening experiment based onmultiple stimulus tests with hidden references and an anchor (MUSHRA) with theMAESTRO. The obtained results indicate that the proposed model exhibits a moresignificant performance and stability improvement than the conventional RAVEmodel.

Conditional variational autoencoder to improve neural audio synthesis for polyphonic music sound