Table 6 Average output SIRs in dB for 2 ×3 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 |
16 | 3.9 | 4.7 | 5.9 |  | −0.5 | −0.8 | 1.1 |
32 | 4.1 | 5.2 | 7.4 |  | −0.6 | −0.7 | 2.9 |
64 | 4.5 | 6.5 | 8.9 | Â | 1.6 | 2.8 | 6.7 |