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

While most research into speech synthesis has focused on synthesizinghigh-quality speech for in-dataset speakers, an equally essential yet unsolvedproblem is synthesizing speech for unseen speakers who are out-of-dataset withlimited reference data, i.e., speaker adaptive speech synthesis. Many studieshave proposed zero-shot speaker adaptive text-to-speech and voice conversionapproaches aimed at this task. However, most current approaches suffer from thedegradation of naturalness and speaker similarity when synthesizing speech forunseen speakers (i.e., speakers not in the training dataset) due to the poorgeneralizability of the model in out-of-distribution data. To address thisproblem, we propose GZS-TV, a generalizable zero-shot speaker adaptivetext-to-speech and voice conversion model. GZS-TV introduces disentangledrepresentation learning for both speaker embedding extraction and timbretransformation to improve model generalization and leverages the representationlearning capability of the variational autoencoder to enhance the speakerencoder. Our experiments demonstrate that GZS-TV reduces performancedegradation on unseen speakers and outperforms all baseline models in multipledatasets.

Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations