NE-PADD combines SpeechNER attention with a deepfake detector via fusion or transfer, reaching 7.89% EER on the new PartialSpoof-NER benchmark.
Grad-stylespeech: Any-speaker adaptive text-to-speech synthesis with dif- fusion models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
NE-PADD: Leveraging Named Entity Knowledge for Robust Partial Audio Deepfake Detection via Attention Aggregation
NE-PADD combines SpeechNER attention with a deepfake detector via fusion or transfer, reaching 7.89% EER on the new PartialSpoof-NER benchmark.