Table 5 Average output SIRs in dB for 5 ×5 case
From: Audio visual speech source separation via improved context dependent association model
T | Alpha digits | Â | Poet verses | ||||
|---|---|---|---|---|---|---|---|
| Â | JADE-AV | GMM-AVSS | MLP-AVSS | Â | JADE-AV | GMM-AVSS | MLP-AVSS |
8 | 4.9 | 11.9 | 13.8 |  | −1.2 | 0.4 | 2.2 |
16 | 16.1 | 21.9 | 24.3 | Â | 10.1 | 10.3 | 11.7 |
32 | 20.3 | 26.2 | 29.4 | Â | 17.0 | 17.2 | 19.1 |