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

Singing voice conversion is to convert a singer's voice to another one'svoice without changing singing content. Recent work shows that unsupervisedsinging voice conversion can be achieved with an autoencoder-based approach[1]. However, the converted singing voice can be easily out of key, showingthat the existing approach cannot model the pitch information precisely. Inthis paper, we propose to advance the existing unsupervised singing voiceconversion method proposed in [1] to achieve more accurate pitch translationand flexible pitch manipulation. Specifically, the proposed PitchNet added anadversarially trained pitch regression network to enforce the encoder networkto learn pitch invariant phoneme representation, and a separate module to feedpitch extracted from the source audio to the decoder network. Our evaluationshows that the proposed method can greatly improve the quality of the convertedsinging voice (2.92 vs 3.75 in MOS). We also demonstrate that the pitch ofconverted singing can be easily controlled during generation by changing thelevels of the extracted pitch before passing it to the decoder network.

PitchNet: Unsupervised Singing Voice Conversion with Pitch Adversarial Network