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

With the development of automatic speech recognition (ASR) and text-to-speech(TTS) technology, high-quality voice conversion (VC) can be achieved byextracting source content information and target speaker information toreconstruct waveforms. However, current methods still require improvement interms of inference speed. In this study, we propose a lightweight VITS-based VCmodel that uses the HuBERT-Soft model to extract content information featureswithout speaker information. Through subjective and objective experiments onsynthesized speech, the proposed model demonstrates competitive results interms of naturalness and similarity. Importantly, unlike the original VITSmodel, we use the inverse short-time Fourier transform (iSTFT) to replace themost computationally expensive part. Experimental results show that our modelcan generate samples at over 5000 kHz on the 3090 GPU and over 250 kHz on thei9-10900K CPU, achieving competitive speed for the same hardware configuration.

QuickVC: Any-to-many Voice Conversion Using Inverse Short-time Fourier Transform for Faster Conversion