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

Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker'svoice without adaptation parameters. By quantizing speech waveform intodiscrete acoustic tokens and modeling these tokens with the language model,recent language model-based TTS models show zero-shot speaker adaptationcapabilities with only a 3-second acoustic prompt of an unseen speaker.However, they are limited by the length of the acoustic prompt, which makes itdifficult to clone personal speaking style. In this paper, we propose a novelzero-shot TTS model with the multi-scale acoustic prompts based on a neuralcodec language model VALL-E. A speaker-aware text encoder is proposed to learnthe personal speaking style at the phoneme-level from the style promptconsisting of multiple sentences. Following that, a VALL-E based acousticdecoder is utilized to model the timbre from the timbre prompt at theframe-level and generate speech. The experimental results show that ourproposed method outperforms baselines in terms of naturalness and speakersimilarity, and can achieve better performance by scaling out to a longer styleprompt.

Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts