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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Cross-speaker style transfer in speech synthesis aims at transferring a stylefrom source speaker to synthesised speech of a target speaker's timbre. Mostprevious approaches rely on data with style labels, but manually-annotatedlabels are expensive and not always reliable. In response to this problem, wepropose Style-Label-Free, a cross-speaker style transfer method, which canrealize the style transfer from source speaker to target speaker without stylelabels. Firstly, a reference encoder structure based on quantized variationalautoencoder (Q-VAE) and style bottleneck is designed to extract discrete stylerepresentations. Secondly, a speaker-wise batch normalization layer is proposedto reduce the source speaker leakage. In order to improve the style extractionability of the reference encoder, a style invariant and contrastive dataaugmentation method is proposed. Experimental results show that the methodoutperforms the baseline. We provide a website with audio samples.

Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis