Speech Emotion Recognition on CASIA (ASR)
55.6ASRTTS-enabled backdoor framework
Evaluation Results
| Method | Links | |
|---|---|---|
| TTS-enabled backdoor frameworkModel Architecture=Wav2Vec2, Poisoning Ratio (ρ)=0.62026.06 | 55.6 | |
| TTS-enabled backdoor frameworkModel Architecture=UniSpeech, Poisoning Ratio (ρ)=0.62026.06 | 50 | |
| TTS-enabled backdoor frameworkModel Architecture=data2vec, Poisoning Ratio (ρ)=0.62026.06 | 45.8 | |
| TTS-enabled backdoor frameworkModel Architecture=WavLM, Poisoning Ratio (ρ)=0.62026.06 | 37.5 |