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

With the rapid advancement in synthetic speech generation technologies, greatinterest in differentiating spoof speech from the natural speech is emerging inthe research community. The identification of these synthetic signals is adifficult task not only for the cutting-edge classification models but also forhumans themselves. To prevent potential adverse effects, it becomes crucial todetect spoof signals. From a forensics perspective, it is also important topredict the algorithm which generated them to identify the forger. This needsan understanding of the underlying attributes of spoof signals which serve as asignature for the synthesizer. This study emphasizes the segments of speechsignals critical in identifying their authenticity by utilizing the Vocal TractSystem(\textit{VTS}) and Voice Source(\textit{VS}) features.  In this paper, we propose a system that detects spoof signals as well asidentifies the corresponding speech-generating algorithm. We achieve 99.58\% inalgorithm classification accuracy. From experiments, we found that a VSfeature-based system gives more attention to the transition of phonemes, while,a VTS feature-based system gives more attention to stationary segments ofspeech signals. We perform model fusion techniques on the VS-based andVTS-based systems to exploit the complementary information to develop a robustclassifier. Upon analyzing the confusion plots we found that WaveRNN is poorlyclassified depicting more naturalness. On the other hand, we identified thatsynthesizer like Waveform Concatenation, and Neural Source Filter is classifiedwith the highest accuracy. Practical implications of this work can aidresearchers from both forensics (leverage artifacts) and the speech communities(mitigate artifacts).

Evince the artifacts of Spoof Speech by blending Vocal Tract and Voice Source Features