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

We present progress towards bilingual Text-to-Speech which is able totransform a monolingual voice to speak a second language while preservingspeaker voice quality. We demonstrate that a bilingual speaker embedding spacecontains a separate distribution for each language and that a simple transformin speaker space generated by the speaker embedding can be used to control thedegree of accent of a synthetic voice in a language. The same transform can beapplied even to monolingual speakers.  In our experiments speaker data from an English-Spanish (Mexican) bilingualspeaker was used, and the goal was to enable English speakers to speak Spanishand Spanish speakers to speak English. We found that the simple transform wassufficient to convert a voice from one language to the other with a high degreeof naturalness. In one case the transformed voice outperformed a nativelanguage voice in listening tests. Experiments further indicated that thetransform preserved many of the characteristics of the original voice. Thedegree of accent present can be controlled and naturalness is relativelyconsistent across a range of accent values.

Generating Multilingual Voices Using Speaker Space Translation Based on Bilingual Speaker Data