From: AUC optimization for deep learning-based voice activity detection
Noise type | SNR | MCE | MMSE | MaxAUCsigm | MaxAUChinge |
---|---|---|---|---|---|
Babble | − 10 dB | 0.6276 | 0.6209 | 0.6324 | 0.6370 |
− 5 dB | 0.7238 | 0.7073 | 0.7278 | 0.7362 | |
0 dB | 0.8165 | 0.7947 | 0.8184 | 0.8269 | |
5 dB | 0.8763 | 0.8586 | 0.8774 | 0.8826 | |
10 dB | 0.9061 | 0.8974 | 0.9080 | 0.9110 | |
15 dB | 0.9223 | 0.9197 | 0.9246 | 0.9280 | |
20 dB | 0.9358 | 0.9345 | 0.9369 | 0.9414 | |
Factory | − 10 dB | 0.7542 | 0.7479 | 0.7618 | 0.7658 |
− 5 dB | 0.8355 | 0.8284 | 0.8414 | 0.8457 | |
0 dB | 0.8813 | 0.8761 | 0.8846 | 0.8873 | |
5 dB | 0.9053 | 0.9017 | 0.9075 | 0.9089 | |
10 dB | 0.9201 | 0.9176 | 0.9219 | 0.9231 | |
15 dB | 0.9314 | 0.9296 | 0.9330 | 0.9349 | |
20 dB | 0.9410 | 0.9390 | 0.9421 | 0.9445 | |
Volvo | − 10 dB | 0.9359 | 0.9352 | 0.9373 | 0.9376 |
− 5 dB | 0.9472 | 0.9459 | 0.9473 | 0.9483 | |
0 dB | 0.9549 | 0.9529 | 0.9543 | 0.9556 | |
5 dB | 0.9594 | 0.9570 | 0.9584 | 0.9599 | |
10 dB | 0.9615 | 0.9588 | 0.9604 | 0.9621 | |
15 dB | 0.9620 | 0.9590 | 0.9607 | 0.9628 | |
20 dB | 0.9616 | 0.9584 | 0.9601 | 0.9628 |