Table 11 LW-BGRU and LW-BrGRU accuracy as a function of the number of layer and hidden layer size
From: Advanced recurrent network-based hybrid acoustic models for low resource speech recognition
# layers | Model | # hidden layer size | ||||
|---|---|---|---|---|---|---|
300 | 500 | 700 | 800 | 900 | ||
2 | A | 48.4 | 47.6 | 47.4 | 47.4 | 48 |
B | 48.1 | 47.3 | 47 | 47.1 | 47.8 | |
C | 43.9 | 43.3 | 43.1 | 43.2 | 44.1 | |
D | 43.7 | 43.1 | 42.7 | 42.9 | 43.5 | |
3 | A | 48.2 | 47.7 | 47.9 | 48.5 | 48.9 |
B | 47.5 | 46.9 | 46.9 | 47.1 | 47.6 | |
C | 43.8 | 43.5 | 43.7 | 44.3 | 44.9 | |
D | 42.9 | 42.6 | 42.6 | 43.1 | 43.5 | |