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

This paper investigates how to leverage a DurIAN-based average model toenable a new speaker to have both accurate pronunciation and fluentcross-lingual speaking with very limited monolingual data. A weakness of therecently proposed end-to-end text-to-speech (TTS) systems is that robustalignment is hard to achieve, which hinders it to scale well with very limiteddata. To cope with this issue, we introduce AdaDurIAN by training an improvedDurIAN-based average model and leverage it to few-shot learning with the sharedspeaker-independent content encoder across different speakers. Several few-shotlearning tasks in our experiments show AdaDurIAN can outperform the baselineend-to-end system by a large margin. Subjective evaluations also show thatAdaDurIAN yields higher mean opinion score (MOS) of naturalness and morepreferences of speaker similarity. In addition, we also apply AdaDurIAN toemotion transfer tasks and demonstrate its promising performance.

AdaDurIAN: Few-shot Adaptation for Neural Text-to-Speech with DurIAN