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

Spontaneous speaking style exhibits notable differences from other speakingstyles due to various spontaneous phenomena (e.g., filled pauses, prolongation)and substantial prosody variation (e.g., diverse pitch and duration variation,occasional non-verbal speech like a smile), posing challenges to modeling andprediction of spontaneous style. Moreover, the limitation of high-qualityspontaneous data constrains spontaneous speech generation for speakers withoutspontaneous data. To address these problems, we propose SponTTS, a two-stageapproach based on neural bottleneck (BN) features to model and transferspontaneous style for TTS. In the first stage, we adopt a ConditionalVariational Autoencoder (CVAE) to capture spontaneous prosody from a BN featureand involve the spontaneous phenomena by the constraint of spontaneousphenomena embedding prediction loss. Besides, we introduce a flow-basedpredictor to predict a latent spontaneous style representation from the text,which enriches the prosody and context-specific spontaneous phenomena duringinference. In the second stage, we adopt a VITS-like module to transfer thespontaneous style learned in the first stage to the target speakers.Experiments demonstrate that SponTTS is effective in modeling spontaneous styleand transferring the style to the target speakers, generating spontaneousspeech with high naturalness, expressiveness, and speaker similarity. Thezero-shot spontaneous style TTS test further verifies the generalization androbustness of SponTTS in generating spontaneous speech for unseen speakers.

SponTTS: modeling and transferring spontaneous style for TTS