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

To realize any-to-any (A2A) voice conversion (VC), most methods are toperform symmetric self-supervised reconstruction tasks (Xi to Xi), whichusually results in inefficient performances due to inadequate featuredecoupling, especially for unseen speakers. We propose a two-stagereconstruction task (Xi to Yi to Xi) using synthetic specific-speaker speechesas intermedium features, where A2A VC is divided into two stages: any-to-one(A2O) and one-to-Any (O2A). In the A2O stage, we propose a new A2O method:SingleVC, by employing a noval data augment strategy(pitch-shifted andduration-remained, PSDR) to accomplish Xi to Yi. In the O2A stage, MediumVC isproposed based on pre-trained SingleVC to conduct Yi to Xi. Through suchasymmetrical reconstruction tasks (Xi to Yi in SingleVC and Yi to Xi inMediumVC), the models are to capture robust disentangled features purposefully.Experiments indicate MediumVC can enhance the similarity of converted speecheswhile maintaining a high degree of naturalness.

MediumVC: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features