NE-PADD combines SpeechNER attention with a deepfake detector via fusion or transfer, reaching 7.89% EER on the new PartialSpoof-NER benchmark.
Enhancing expressive voice conversion with discrete pitch-conditioned flow matching model,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 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.