SynHate provides 134,797 audio clips across 37 languages with real/fake and normal/hate labels; Whisper-small is the best tested baseline at about 85% accuracy.
Tacotron: Towards end-to-end speech synthesis,
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.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SynHate: Detecting Hate Speech in Synthetic Deepfake Audio
SynHate provides 134,797 audio clips across 37 languages with real/fake and normal/hate labels; Whisper-small is the best tested baseline at about 85% accuracy.