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

End-to-end text-to-speech synthesis (TTS), which generates speech soundsdirectly from strings of texts or phonemes, has improved the quality of speechsynthesis over the conventional TTS. However, most previous studies have beenevaluated based on subjective naturalness and have not objectively examinedwhether they can reproduce pitch patterns of phonological phenomena such asdownstep, rhythmic boost, and initial lowering that reflect syntacticstructures in Japanese. These phenomena can be linguistically explained byphonological constraints and the syntax$\unicode{x2013}$prosody mappinghypothesis (SPMH), which assumes projections from syntactic structures tophonological hierarchy. Although some experiments in psycholinguistics haveverified the validity of the SPMH, it is crucial to investigate whether it canbe implemented in TTS. To synthesize linguistic phenomena involving syntacticor phonological constraints, we propose a model using phonological symbolsbased on the SPMH and prosodic well-formedness constraints. Experimentalresults showed that the proposed method synthesized similar pitch patterns tothose reported in linguistics experiments for the phenomena of initial loweringand rhythmic boost. The proposed model efficiently synthesizes phonologicalphenomena in the test data that were not explicitly included in the trainingdata.

Applying Syntax$\unicode{x2013}$Prosody Mapping Hypothesis and Prosodic Well-Formedness Constraints to Neural Sequence-to-Sequence Speech Synthesis