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

Comparing with traditional text-to-speech (TTS) systems, conversational TTSsystems are required to synthesize speeches with proper speaking styleconfirming to the conversational context. However, state-of-the-art contextmodeling methods in conversational TTS only model the textual information incontext with a recurrent neural network (RNN). Such methods have limitedability in modeling the inter-speaker influence in conversations, and alsoneglect the speaking styles and the intra-speaker inertia inside each speaker.Inspired by DialogueGCN and its superiority in modeling such conversationalinfluences than RNN based approaches, we propose a graph-based multi-modalcontext modeling method and adopt it to conversational TTS to enhance thespeaking styles of synthesized speeches. Both the textual and speaking styleinformation in the context are extracted and processed by DialogueGCN to modelthe inter- and intra-speaker influence in conversations. The outputs ofDialogueGCN are then summarized by attention mechanism, and converted to theenhanced speaking style for current utterance. An English conversation corpusis collected and annotated for our research and released to public. Experimentresults on this corpus demonstrate the effectiveness of our proposed approach,which outperforms the state-of-the-art context modeling method inconversational TTS in both MOS and ABX preference rate.

Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling