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

Cross-speaker style transfer in speech synthesis aims at transferring a stylefrom source speaker to synthesized speech of a target speaker's timbre. In mostprevious methods, the synthesized fine-grained prosody features often representthe source speaker's average style, similar to the one-to-many problem(i.e.,multiple prosody variations correspond to the same text). In response to thisproblem, a strength-controlled semi-supervised style extractor is proposed todisentangle the style from content and timbre, improving the representation andinterpretability of the global style embedding, which can alleviate theone-to-many mapping and data imbalance problems in prosody prediction. Ahierarchical prosody predictor is proposed to improve prosody modeling. We findthat better style transfer can be achieved by using the source speaker'sprosody features that are easily predicted. Additionally, aspeaker-transfer-wise cycle consistency loss is proposed to assist the model inlearning unseen style-timbre combinations during the training phase.Experimental results show that the method outperforms the baseline. We providea website with audio samples.

Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis