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 the context of spoofing attacks in speaker recognition systems, weobserved that the waveform probability mass function (PMF) of genuine speechdiffers significantly from the PMF of speech resulting from the attacks. Thisis true for synthesized or converted speech as well as replayed speech. We alsonoticed that this observation seems to have a significant impact on spoofingdetection performance. In this article, we propose an algorithm, denotedgenuinization, capable of reducing the waveform distribution gap betweenauthentic speech and spoofing speech. Our genuinization algorithm is evaluatedon ASVspoof 2019 challenge datasets, using the baseline system provided by thechallenge organization. We first assess the influence of genuinization onspoofing performance. Using genuinization for the spoofing attacks degradesspoofing detection performance by up to a factor of 10. Next, we integrate thegenuinization algorithm in the spoofing countermeasures and we observe a hugespoofing detection improvement in different cases. The results of ourexperiments show clearly that waveform distribution plays an important role andmust be taken into account by anti-spoofing systems.

Thech. Report: Genuinization of Speech waveform PMF for speaker detection spoofing and countermeasures