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.
Our analysis showed current anti-spoofing paradigm with datasets and methods without emotional focus strug- gle with emotion-targeted attacks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 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.