quiz bu lëkkale ak tegtal · Diggante Niveau

Audio ngir gis Deepfake

Xoolaat àppu gis-gis audio-spoof, yamale référence, efekti kompresioŋ, ak li provenance siñe mëna am ak limu mënu.

Yooni njiit yu jëm ciGis Deepfake Audio
Laaj 1 de 8

Lan mooy mébetu detektëru deepfake audio?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Lan mooy mébetu detektëru deepfake audio?
    • Ngir xam ndax wax ji dëgg la wala IA moo ko defar
    • Ngir gëna baaxal kalite son bi ci enregistremaa bi
    • Ngir soppi kàddu yi ci mbind
    • Ngir kompresse fichier audio
  2. In “Does Audio Deepfake Detection Generalize?”, which feature comparison improved performance in the authors’ controlled evaluation?
    • Raw transcript tokens instead of audio
    • CQT or log-spectrogram features instead of mel-spectrogram features
    • A larger waveform file instead of a smaller one
    • Video frames instead of speech features
  3. Lan moo waral ñuy woowe gis-gis audio deepfake ni 'dawal gànnaay'?
    • Detektër yi dañuy dox ci kaw jumtukaayi soldaar yi
    • Fichier audio yi dañuy gëna rëy
    • Pexem synthese yu bees yi deñuy moytu detektër yiñ tàggat ci njuumte yu yàgg yi
    • Dafay laaj ñaari nit ngir doxal
  4. Lan la benchmark ASVspoof bu siiw bi di jàngat?
    • Kalite music biñu lay digal
    • Tekki mbind bu jaar yoon
    • Realism defar nataal
    • Gis-gis buy tere nax/deepfake ngir wax
  5. What can a valid C2PA Content Credential help a verifier check?
    • A signed record of an asset’s provenance and edit history
    • That every spoken claim in the audio is true
    • The speaker’s real-world identity in all cases
    • That a recording has never been compressed
  6. What input type did the ASVspoof 2021 Deepfake task target?
    • Uncompressed music recordings from a studio
    • Manipulated, compressed speech posted online
    • Images altered by face-swapping systems
    • Only live telephone conversations with known speakers
  7. How large was the real-world dataset collected in the cited audio deepfake generalization study?
    • 3.79 hours total, all authentic speech
    • 37.9 hours of deepfakes with no authentic audio
    • 37.9 hours total, including 17.2 hours of deepfakes
    • 172 hours total, including 17.2 hours of deepfakes
  8. What does the absence of a C2PA credential establish?
    • That the recording is necessarily a deepfake
    • That the recording has no edits
    • That the speaker is verified
    • Nothing by itself about whether the media is authentic or synthetic