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

Cross-speaker style transfer (CSST) in text-to-speech (TTS) synthesis aims attransferring a speaking style to the synthesised speech in a target speaker'svoice. Most previous CSST approaches rely on expensive high-quality datacarrying desired speaking style during training and require a referenceutterance to obtain speaking style descriptors as conditioning on thegeneration of a new sentence. This work presents Referee, a robustreference-free CSST approach for expressive TTS, which fully leverageslow-quality data to learn speaking styles from text. Referee is built bycascading a text-to-style (T2S) model with a style-to-wave (S2W) model.Phonetic PosteriorGram (PPG), phoneme-level pitch and energy contours areadopted as fine-grained speaking style descriptors, which are predicted fromtext using the T2S model. A novel pretrain-refinement method is adopted tolearn a robust T2S model by only using readily accessible low-quality data. TheS2W model is trained with high-quality target data, which is adopted toeffectively aggregate style descriptors and generate high-fidelity speech inthe target speaker's voice. Experimental results are presented, showing thatReferee outperforms a global-style-token (GST)-based baseline approach in CSST.

Referee: Towards reference-free cross-speaker style transfer with low-quality data for expressive speech synthesis