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

Text-based speech editing (TSE) techniques are designed to enable users toedit the output audio by modifying the input text transcript instead of theaudio itself. Despite much progress in neural network-based TSE techniques, thecurrent techniques have focused on reducing the difference between thegenerated speech segment and the reference target in the editing region,ignoring its local and global fluency in the context and original utterance. Tomaintain the speech fluency, we propose a fluency speech editing model, termed\textit{FluentEditor}, by considering fluency-aware training criterion in theTSE training. Specifically, the \textit{acoustic consistency constraint} aimsto smooth the transition between the edited region and its neighboring acousticsegments consistent with the ground truth, while the \textit{prosodyconsistency constraint} seeks to ensure that the prosody attributes within theedited regions remain consistent with the overall style of the originalutterance. The subjective and objective experimental results on VCTKdemonstrate that our \textit{FluentEditor} outperforms all advanced baselinesin terms of naturalness and fluency. The audio samples and code are availableat \url{https://github.com/Ai-S2-Lab/FluentEditor}.

FluentEditor: Text-based Speech Editing by Considering Acoustic and Prosody Consistency