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

A good training set for speech spoofing countermeasures requires diverse TTSand VC spoofing attacks, but generating TTS and VC spoofed trials for a targetspeaker may be technically demanding. Instead of using full-fledged TTS and VCsystems, this study uses neural-network-based vocoders to do copy-synthesis onbona fide utterances. The output data can be used as spoofed data. To makebetter use of pairs of bona fide and spoofed data, this study introduces acontrastive feature loss that can be plugged into the standard trainingcriterion. On the basis of the bona fide trials from the ASVspoof 2019 logicalaccess training set, this study empirically compared a few training setscreated in the proposed manner using a few neural non-autoregressive vocoders.Results on multiple test sets suggest good practices such as fine-tuning neuralvocoders using bona fide data from the target domain. The results alsodemonstrated the effectiveness of the contrastive feature loss. Combining thebest practices, the trained CM achieved overall competitive performance. ItsEERs on the ASVspoof 2021 hidden subsets also outperformed the top-1 challengesubmission.

Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders