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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper presents a novel design of neural network system for fine-grainedstyle modeling, transfer and prediction in expressive text-to-speech (TTS)synthesis. Fine-grained modeling is realized by extracting style embeddingsfrom the mel-spectrograms of phone-level speech segments. Collaborativelearning and adversarial learning strategies are applied in order to achieveeffective disentanglement of content and style factors in speech and alleviatethe "content leakage" problem in style modeling. The proposed system can beused for varying-content speech style transfer in the single-speaker scenario.The results of objective and subjective evaluation show that our systemperforms better than other fine-grained speech style transfer models,especially in the aspect of content preservation. By incorporating a stylepredictor, the proposed system can also be used for text-to-speech synthesis.Audio samples are provided for system demonstrationhttps://daxintan-cuhk.github.io/pl-csd-speech .

Fine-grained Style Modeling, Transfer and Prediction in Text-to-Speech Synthesis via Phone-Level Content-Style Disentanglement