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

This paper explores the potential of constructing an AI spoken dialoguesystem that "thinks how to respond" and "thinks how to speak" simultaneously,which more closely aligns with the human speech production process compared tothe current cascade pipeline of independent chatbot and Text-to-Speech (TTS)modules. We hypothesize that Large Language Models (LLMs) with billions ofparameters possess significant speech understanding capabilities and canjointly model dialogue responses and linguistic features. We conduct two setsof experiments: 1) Prosodic structure prediction, a typical front-end task inTTS, demonstrating the speech understanding ability of LLMs, and 2) Furtherintegrating dialogue response and a wide array of linguistic features using aunified encoding format. Our results indicate that the LLM-based approach is apromising direction for building unified spoken dialogue systems.

Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model