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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain successin the situation where a lot of high-quality speech plus their correspondingtranscriptions are available. However, laborious paired data collectionprocesses prevent many institutes from building multi-speaker TTS systems ofgreat performance. In this work, we propose a semi-supervised learning approachfor multi-speaker TTS. A multi-speaker TTS model can learn from theuntranscribed audio via the proposed encoder-decoder framework with discretespeech representation. The experiment results demonstrate that with only anhour of paired speech data, no matter the paired data is from multiple speakersor a single speaker, the proposed model can generate intelligible speech indifferent voices. We found the model can benefit from the proposedsemi-supervised learning approach even when part of the unpaired speech data isnoisy. In addition, our analysis reveals that different speaker characteristicsof the paired data have an impact on the effectiveness of semi-supervised TTS.

Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation