Small semantic-preserving changes to transcripts, passed through text-to-speech, significantly reduce the accuracy of both open-source and commercial audio anti-spoofing detectors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
Small semantic-preserving changes to transcripts, passed through text-to-speech, significantly reduce the accuracy of both open-source and commercial audio anti-spoofing detectors.