Speech Emotion Recognition on ANAD
100ASRTTS-enabled backdoor framework
Evaluation Results
| Method | Links | |
|---|---|---|
| TTS-enabled backdoor frameworkModel Architecture=data2vec, Poisoning Ratio (ρ)=0.62026.06 | 100 | |
| TTS-enabled backdoor frameworkModel Architecture=Wav2Vec2, Poisoning Ratio (ρ)=0.62026.06 | 98.7 | |
| TTS-enabled backdoor frameworkModel Architecture=UniSpeech, Poisoning Ratio (ρ)=0.62026.06 | 97.3 | |
| TTS-enabled backdoor frameworkModel Architecture=WavLM, Poisoning Ratio (ρ)=0.62026.06 | 88 |