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

The quest for comprehensive generative models of intonation that linklinguistic and paralinguistic functions to prosodic forms has been alongstanding challenge of speech communication research. Traditional intonationmodels have given way to the overwhelming performance of deep learning (DL)techniques for training general purpose end-to-end mappings using millions oftunable parameters. The shift towards black box machine learning models hasnonetheless posed the reverse problem -- a compelling need to discoverknowledge, to explain, visualise and interpret. Our work bridges between acomprehensive generative model of intonation and state-of-the-art DLtechniques. We build upon the modelling paradigm of the Superposition ofFunctional Contours (SFC) model and propose a Variational Prosody Model (VPM)that uses a network of variational contour generators to capture thecontext-sensitive variation of the constituent elementary prosodic contours. Weshow that the VPM can give insight into the intrinsic variability of theseprosodic prototypes through learning a meaningful prosodic latent spacerepresentation structure. We also show that the VPM is able to capture prosodicphenomena that have multiple dimensions of context based variability. Since itis based on the principle of superposition, the VPM does not necessitate theuse of specially crafted corpora for the analysis, opening up the possibilitiesof using big data for prosody analysis. In a speech synthesis scenario, themodel can be used to generate a dynamic and natural prosody contour that isdevoid of averaging effects.

A Variational Prosody Model for Mapping the Context-Sensitive Variation of Functional Prosodic Prototypes