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

Current synthetic speech detection (SSD) methods perform well on certaindatasets but still face issues of robustness and interpretability. A possiblereason is that these methods do not analyze the deficiencies of syntheticspeech. In this paper, the flaws of the speaker features inherent in thetext-to-speech (TTS) process are analyzed. Differences in the temporalconsistency of intra-utterance speaker features arise due to the lack offine-grained control over speaker features in TTS. Since the speakerrepresentations in TTS are based on speaker embeddings extracted by encoders,the distribution of inter-utterance speaker features differs between syntheticand bonafide speech. Based on these analyzes, an SSD method based on temporalconsistency and distribution of speaker features is proposed. On one hand,modeling the temporal consistency of intra-utterance speaker features can aidspeech anti-spoofing. On the other hand, distribution differences ininter-utterance speaker features can be utilized for SSD. The proposed methodoffers low computational complexity and performs well in both cross-dataset andsilence trimming scenarios.

Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features