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

Text-based voice editing (TBVE) uses synthetic output from text-to-speech(TTS) systems to replace words in an original recording. Recent work has usedneural models to produce edited speech that is similar to the original speechin terms of clarity, speaker identity, and prosody. However, one limitation ofprior work is the usage of finetuning to optimise performance: this requiresfurther model training on data from the target speaker, which is a costlyprocess that may incorporate potentially sensitive data into server-sidemodels. In contrast, this work focuses on the zero-shot approach which avoidsfinetuning altogether, and instead uses pretrained speaker verificationembeddings together with a jointly trained reference encoder to encodeutterance-level information that helps capture aspects such as speaker identityand prosody. Subjective listening tests find that both utterance embeddings anda reference encoder improve the continuity of speaker identity and prosodybetween the edited synthetic speech and unedited original recording in thezero-shot setting.

Towards zero-shot Text-based voice editing using acoustic context conditioning, utterance embeddings, and reference encoders