Table 3 Detailed architecture of the CNN-RNN model used as the ASR module
From: Accent modification for speech recognition of non-native speakers using neural style transfer
Layer | Output shape | Parameters |
|---|---|---|
InputLayer | B, T, 161 | 0 |
Conv1D (F=250, K=3) | B, T, 250 | 443000 |
Conv1D (F=250, K=3) | B, T, 250 | 443000 |
Maxpool (P=2) | B, T, 250 | 940 |
Conv1D (F=150, K=3) | B, T, 150 | 265800 |
Conv1D (F=150, K=3) | B, T, 150 | 265800 |
Maxpool (P=2) | B, T, 150 | 600 |
Conv1D (F=100, K=3) | B, T, 100 | 177200 |
Conv1D (F=100, K=3) | B, T, 100 | 177200 |
Maxpool (P=2) | B, T, 100 | 400 |
Conv1D (F=80, K=3) | B, T, 80 | 141760 |
Conv1D (F=80, K=3) | B, T, 80 | 141760 |
Bidirectional (U=200) | B, T, 400 | 505200 |
BatchNormalization | B, T, 400 | 1600 |
TimeDistributed | B, T, 29 | 11629 |
Dropout | B, T, 29 | 0 |
TimeDistributed | B, T, 29 | 870 |
SoftmaxActivation | B, T, 29 | 0 |
| Â | Total params: | 2,576,759 |
| Â | Trainable params: | 2,576,759 |
| Â | Non-trainable params: | 0 |