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

To further improve the speaking styles of synthesized speeches, currenttext-to-speech (TTS) synthesis systems commonly employ reference speeches tostylize their outputs instead of just the input texts. These reference speechesare obtained by manual selection which is resource-consuming, or selected bysemantic features. However, semantic features contain not only style-relatedinformation, but also style irrelevant information. The information irrelevantto speaking style in the text could interfere the reference audio selection andresult in improper speaking styles. To improve the reference selection, wepropose Contrastive Acoustic-Linguistic Module (CALM) to extract theStyle-related Text Feature (STF) from the text. CALM optimizes the correlationbetween the speaking style embedding and the extracted STF with contrastivelearning. Thus, a certain number of the most appropriate reference speeches forthe input text are selected by retrieving the speeches with the top STFsimilarities. Then the style embeddings are weighted summarized according totheir STF similarities and used to stylize the synthesized speech of TTS.Experiment results demonstrate the effectiveness of our proposed approach, withboth objective evaluations and subjective evaluations on the speaking styles ofthe synthesized speeches outperform a baseline approach withsemantic-feature-based reference selection.

CALM: Contrastive Cross-modal Speaking Style Modeling for Expressive Text-to-Speech Synthesis