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

It was shown recently that a combination of ASR and TTS models yield highlycompetitive performance on standard voice conversion tasks such as the VoiceConversion Challenge 2020 (VCC2020). To obtain good performance both modelsrequire pretraining on large amounts of data, thereby obtaining large modelsthat are potentially inefficient in use. In this work we present a model thatis significantly smaller and thereby faster in processing while obtainingequivalent performance. To achieve this the proposed model, Dynamic-GAN-VC(DYGAN-VC), uses a non-autoregressive structure and makes use of vectorquantised embeddings obtained from a VQWav2vec model. Furthermore dynamicconvolution is introduced to improve speech content modeling while requiring asmall number of parameters. Objective and subjective evaluation was performedusing the VCC2020 task, yielding MOS scores of up to 3.86, and character errorrates as low as 4.3\%. This was achieved with approximately half the number ofmodel parameters, and up to 8 times faster decoding speed.

Efficient Non-Autoregressive GAN Voice Conversion using VQWav2vec Features and Dynamic Convolution