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

This paper studies a transferable phoneme embedding framework that aims todeal with the cross-lingual text-to-speech (TTS) problem under the few-shotsetting. Transfer learning is a common approach when it comes to few-shotlearning since training from scratch on few-shot training data is bound tooverfit. Still, we find that the naive transfer learning approach fails toadapt to unseen languages under extremely few-shot settings, where less than 8minutes of data is provided. We deal with the problem by proposing a frameworkthat consists of a phoneme-based TTS model and a codebook module to projectphonemes from different languages into a learned latent space. Furthermore, byutilizing phoneme-level averaged self-supervised learned features, weeffectively improve the quality of synthesized speeches. Experiments show thatusing 4 utterances, which is about 30 seconds of data, is enough to synthesizeintelligible speech when adapting to an unseen language using our framework.

Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embedding