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

Recent advances in text-to-speech, particularly those based on Graph NeuralNetworks (GNNs), have significantly improved the expressiveness of short-formsynthetic speech. However, generating human-parity long-form speech with highdynamic prosodic variations is still challenging. To address this problem, weexpand the capabilities of GNNs with a hierarchical prosody modeling approach,named HiGNN-TTS. Specifically, we add a virtual global node in the graph tostrengthen the interconnection of word nodes and introduce a contextualattention mechanism to broaden the prosody modeling scope of GNNs fromintra-sentence to inter-sentence. Additionally, we perform hierarchicalsupervision from acoustic prosody on each node of the graph to capture theprosodic variations with a high dynamic range. Ablation studies show theeffectiveness of HiGNN-TTS in learning hierarchical prosody. Both objective andsubjective evaluations demonstrate that HiGNN-TTS significantly improves thenaturalness and expressiveness of long-form synthetic speech.

HiGNN-TTS: Hierarchical Prosody Modeling with Graph Neural Networks for Expressive Long-form TTS