Table 7 Training time per epoch (hours) vs. the length of local window
From: Advanced recurrent network-based hybrid acoustic models for low resource speech recognition
Model | The length of local window | Â | |||
|---|---|---|---|---|---|
| Â | 10 | 20 | 30 | 40 | 50 |
LW-BLSTM-fbank | 3.92 | 4.71 | 5.03 | 5.34 | 5.68 |
BLSTM-fbank | Â | Â | 8.40 | Â | |
LW-BLSTM-MBN | 3.92 | 4.71 | 5.01 | 5.34 | 5.70 |
BLSTM-MBN | Â | Â | 8.40 | Â | |