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

Conversational text-to-speech (TTS) aims to synthesize speech with properprosody of reply based on the historical conversation. However, it is still achallenge to comprehensively model the conversation, and a majority ofconversational TTS systems only focus on extracting global information and omitlocal prosody features, which contain important fine-grained information likekeywords and emphasis. Moreover, it is insufficient to only consider thetextual features, and acoustic features also contain various prosodyinformation. Hence, we propose M2-CTTS, an end-to-end multi-scale multi-modalconversational text-to-speech system, aiming to comprehensively utilizehistorical conversation and enhance prosodic expression. More specifically, wedesign a textual context module and an acoustic context module with bothcoarse-grained and fine-grained modeling. Experimental results demonstrate thatour model mixed with fine-grained context information and additionallyconsidering acoustic features achieves better prosody performance andnaturalness in CMOS tests.

M2-CTTS: End-to-End Multi-scale Multi-modal Conversational Text-to-Speech Synthesis