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-lingual timbre and style generalizable text-to-speech (TTS) aims tosynthesize speech with a specific reference timbre or style that is nevertrained in the target language. It encounters the following challenges: 1)timbre and pronunciation are correlated since multilingual speech of a specificspeaker is usually hard to obtain; 2) style and pronunciation are mixed becausethe speech style contains language-agnostic and language-specific parts. Toaddress these challenges, we propose GenerTTS, which mainly includes thefollowing works: 1) we elaborately design a HuBERT-based information bottleneckto disentangle timbre and pronunciation/style; 2) we minimize the mutualinformation between style and language to discard the language-specificinformation in the style embedding. The experiments indicate that GenerTTSoutperforms baseline systems in terms of style similarity and pronunciationaccuracy, and enables cross-lingual timbre and style generalization.

GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech