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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recently, there has been a growing interest in the field of controllableText-to-Speech (TTS). While previous studies have relied on users providingspecific style factor values based on acoustic knowledge or selecting referencespeeches that meet certain requirements, generating speech solely from naturaltext prompts has emerged as a new challenge for researchers. This challengearises due to the scarcity of high-quality speech datasets with natural textstyle prompt and the absence of advanced text-controllable TTS models. In lightof this, 1) we propose TextrolSpeech, which is the first large-scale speechemotion dataset annotated with rich text attributes. The dataset comprises236,220 pairs of style prompt in natural text descriptions with five stylefactors and corresponding speech samples. Through iterative experimentation, weintroduce a multi-stage prompt programming approach that effectively utilizesthe GPT model for generating natural style descriptions in large volumes. 2)Furthermore, to address the need for generating audio with greater stylediversity, we propose an efficient architecture called Salle. This architecturetreats text controllable TTS as a language model task, utilizing audio codeccodes as an intermediate representation to replace the conventionalmel-spectrogram. Finally, we successfully demonstrate the ability of theproposed model by showing a comparable performance in the controllable TTStask. Audio samples are available at https://sall-e.github.io/

TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models