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/

Zendy Plus

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

Zendy Tools

Zendy Open

This paper investigates the use of generative adversarial network (GAN)-basedmodels for converting the spectrogram of a speech signal into that of a singingone, without reference to the phoneme sequence underlying the speech. This isachieved by viewing speech-to-singing conversion as a style transfer problem.Specifically, given a speech input, and optionally the F0 contour of the targetsinging, the proposed model generates as the output a singing signal with aprogressive-growing encoder/decoder architecture and boundary equilibrium GANloss functions. Our quantitative and qualitative analysis show that theproposed model generates singing voices with much higher naturalness than anexisting non adversarially-trained baseline. For reproducibility, the code willbe publicly available at a GitHub repository upon paper publication.

Speech-to-Singing Conversion based on Boundary Equilibrium GAN