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

Current end-to-end autoregressive TTS systems (e.g. Tacotron 2) haveoutperformed traditional parallel approaches on the quality of synthesizedspeech. However, they introduce new problems at the same time. Due to theautoregressive nature, the time cost of inference has to be proportional to thelength of text, which pose a great challenge for online serving. On the otherhand, the style of synthetic speech becomes unstable and may change obviouslyamong sentences. In this paper, we propose a Phrase based Parallel End-to-EndTTS System (PPSpeech) to address these issues. PPSpeech uses autoregressionapproach within a phrase and executes parallel strategies for differentphrases. By this method, we can achieve both high quality and high efficiency.In addition, we propose acoustic embedding and text context embedding as theconditions of encoder to keep successive and prevent from abrupt style ortimbre change. Experiments show that, the synthesis speed of PPSpeech is muchfaster than sentence level autoregressive Tacotron 2 when a sentence has morethan 5 phrases. The speed advantage increases with the growth of sentencelength. Subjective experiments show that the proposed system with acousticembedding and context embedding as conditions can make the style transitionacross sentences gradient and natural, defeating Global Style Token (GST)obviously in MOS.

PPSpeech: Phrase based Parallel End-to-End TTS System