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

In this paper, we present an open-source software for developing anonparallel voice conversion (VC) system named crank. Although we have releasedan open-source VC software based on the Gaussian mixture model named sprocketin the last VC Challenge, it is not straightforward to apply any speech corpusbecause it is necessary to prepare parallel utterances of source and targetspeakers to model a statistical conversion function. To address this issue, inthis study, we developed a new open-source VC software that enables users tomodel the conversion function by using only a nonparallel speech corpus. Forimplementing the VC software, we used a vector-quantized variationalautoencoder (VQVAE). To rapidly examine the effectiveness of recenttechnologies developed in this research field, crank also supports severalrepresentative works for autoencoder-based VC methods such as the use ofhierarchical architectures, cyclic architectures, generative adversarialnetworks, speaker adversarial training, and neural vocoders. Moreover, it ispossible to automatically estimate objective measures such as mel-cepstrumdistortion and pseudo mean opinion score based on MOSNet. In this paper, wedescribe representative functions developed in crank and make brief comparisonsby objective evaluations.

crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder