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

Building cross-lingual voice conversion (VC) systems for multiple speakersand multiple languages has been a challenging task for a long time. This paperdescribes a parallel non-autoregressive network to achieve bilingual andcode-switched voice conversion for multiple speakers when there are onlymono-lingual corpora for each language. We achieve cross-lingual VC betweenMandarin speech with multiple speakers and English speech with multiplespeakers by applying bilingual bottleneck features. To boost voice cloningperformance, we use an adversarial speaker classifier with a gradient reversallayer to reduce the source speaker's information from the output of encoder.Furthermore, in order to improve speaker similarity between reference speechand converted speech, we adopt an embedding consistency loss between thesynthesized speech and its natural reference speech in our network.Experimental results show that our proposed method can achieve high qualityconverted speech with mean opinion score (MOS) around 4. The conversion systemperforms well in terms of speaker similarity for both in-set speaker conversionand out-set-of one-shot conversion.

Building Bilingual and Code-Switched Voice Conversion with Limited Training Data Using Embedding Consistency Loss