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

Incremental text-to-speech (TTS) synthesis generates utterances in smalllinguistic units for the sake of real-time and low-latency applications. Wepreviously proposed an incremental TTS method that leverages a largepre-trained language model to take unobserved future context into accountwithout waiting for the subsequent segment. Although this method achievescomparable speech quality to that of a method that waits for the futurecontext, it entails a huge amount of processing for sampling from the languagemodel at each time step. In this paper, we propose an incremental TTS methodthat directly predicts the unobserved future context with a lightweight model,instead of sampling words from the large-scale language model. We performknowledge distillation from a GPT2-based context prediction network into asimple recurrent model by minimizing a teacher-student loss defined between thecontext embedding vectors of those models. Experimental results show that theproposed method requires about ten times less inference time to achievecomparable synthetic speech quality to that of our previous method, and it canperform incremental synthesis much faster than the average speaking speed ofhuman English speakers, demonstrating the availability of our method toreal-time applications.

Low-Latency Incremental Text-to-Speech Synthesis with Distilled Context Prediction Network