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 advancements in end-to-end speech synthesis have made it possible togenerate highly natural speech. However, training these models typicallyrequires a large amount of high-fidelity speech data, and for unseen texts, theprosody of synthesized speech is relatively unnatural. To address these issues,we propose to combine a fine-tuned BERT-based front-end with a pre-trainedFastSpeech2-based acoustic model to improve prosody modeling. The pre-trainedBERT is fine-tuned on the polyphone disambiguation task, the joint Chinese wordsegmentation (CWS) and part-of-speech (POS) tagging task, and the prosodystructure prediction (PSP) task in a multi-task learning framework. FastSpeech2 is pre-trained on large-scale external data that are noisy but easier toobtain. Experimental results show that both the fine-tuned BERT model and thepre-trained FastSpeech 2 can improve prosody, especially for those structurallycomplex sentences.

Improving Prosody for Unseen Texts in Speech Synthesis by Utilizing Linguistic Information and Noisy Data