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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The expressive quality of synthesized speech for audiobooks is limited bygeneralized model architecture and unbalanced style distribution in thetraining data. To address these issues, in this paper, we propose aself-supervised style enhancing method with VQ-VAE-based pre-training forexpressive audiobook speech synthesis. Firstly, a text style encoder ispre-trained with a large amount of unlabeled text-only data. Secondly, aspectrogram style extractor based on VQ-VAE is pre-trained in a self-supervisedmanner, with plenty of audio data that covers complex style variations. Then anovel architecture with two encoder-decoder paths is specially designed tomodel the pronunciation and high-level style expressiveness respectively, withthe guidance of the style extractor. Both objective and subjective evaluationsdemonstrate that our proposed method can effectively improve the naturalnessand expressiveness of the synthesized speech in audiobook synthesis especiallyfor the role and out-of-domain scenarios.

StyleSpeech: Self-supervised Style Enhancing with VQ-VAE-based Pre-training for Expressive Audiobook Speech Synthesis