Emotional synthetic speech from zero-shot TTS fools the pre-trained RawNet2 anti-spoofing model, and a gated ensemble of emotion-specialized detectors reduces the error and the emotion gap.
As a result, they are unreliable with emo- tional speech, making them vulnerable to emotion-targeted at- tacks
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
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Can Emotion Fool Anti-spoofing?
Emotional synthetic speech from zero-shot TTS fools the pre-trained RawNet2 anti-spoofing model, and a gated ensemble of emotion-specialized detectors reduces the error and the emotion gap.