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

Recent strides in neural speech synthesis technologies, while enjoyingwidespread applications, have nonetheless introduced a series of challenges,spurring interest in the defence against the threat of misuse and abuse.Notably, source attribution of synthesized speech has value in forensics andintellectual property protection, but prior work in this area has certainlimitations in scope. To address the gaps, we present our findings concerningthe identification of the sources of synthesized speech in this paper. Weinvestigate the existence of speech synthesis model fingerprints in thegenerated speech waveforms, with a focus on the acoustic model and the vocoder,and study the influence of each component on the fingerprint in the overallspeech waveforms. Our research, conducted using the multi-speaker LibriTTSdataset, demonstrates two key insights: (1) vocoders and acoustic models impartdistinct, model-specific fingerprints on the waveforms they generate, and (2)vocoder fingerprints are the more dominant of the two, and may mask thefingerprints from the acoustic model. These findings strongly suggest theexistence of model-specific fingerprints for both the acoustic model and thevocoder, highlighting their potential utility in source identificationapplications.

Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms