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

Better disentanglement of speech representation is essential to improve thequality of voice conversion. Recently contrastive learning is applied to voiceconversion successfully based on speaker labels. However, the performance ofmodel will reduce in conversion between similar speakers. Hence, we propose anaugmented negative sample selection to address the issue. Specifically, wecreate hard negative samples based on the proposed speaker fusion module toimprove learning ability of speaker encoder. Furthermore, considering thefine-grain modeling of speaker style, we employ a reference encoder to extractfine-grained style and conduct the augmented contrastive learning on globalstyle. The experimental results show that the proposed method outperformsprevious work in voice conversion tasks.

CLN-VC: Text-Free Voice Conversion Based on Fine-Grained Style Control and Contrastive Learning with Negative Samples Augmentation