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

Generative AI has demonstrated impressive performance in various fields,among which speech synthesis is an interesting direction. With the diffusionmodel as the most popular generative model, numerous works have attempted twoactive tasks: text to speech and speech enhancement. This work conducts asurvey on audio diffusion model, which is complementary to existing surveysthat either lack the recent progress of diffusion-based speech synthesis orhighlight an overall picture of applying diffusion model in multiple fields.Specifically, this work first briefly introduces the background of audio anddiffusion model. As for the text-to-speech task, we divide the methods intothree categories based on the stage where diffusion model is adopted: acousticmodel, vocoder and end-to-end framework. Moreover, we categorize various speechenhancement tasks by either certain signals are removed or added into the inputspeech. Comparisons of experimental results and discussions are also covered inthis survey.

A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI