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

Large language models (LLMs) have gained considerable attention forArtificial Intelligence Generated Content (AIGC), particularly with theemergence of ChatGPT. However, the direct adaptation of continuous speech toLLMs that process discrete tokens remains an unsolved challenge, hindering theapplication of LLMs for speech generation. The advanced speech LMs are in thecorner, as that speech signals encapsulate a wealth of information, includingspeaker and emotion, beyond textual data alone. Prompt tuning has demonstratednotable gains in parameter efficiency and competitive performance on somespeech classification tasks. However, the extent to which prompts caneffectively elicit generation tasks from speech LMs remains an open question.In this paper, we present pioneering research that explores the application ofprompt tuning to stimulate speech LMs for various generation tasks, within aunified framework called SpeechGen, with around 10M trainable parameters. Theproposed unified framework holds great promise for efficiency andeffectiveness, particularly with the imminent arrival of advanced speech LMs,which will significantly enhance the capabilities of the framework. The codeand demos of SpeechGen will be available on the project website:\url{https://ga642381.github.io/SpeechPrompt/speechgen}

SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts