3
$\begingroup$

Iam training a Keras model for end-to-end speech recognition. I have my own dataset of speech containing about 400 wave files. Text transcriptions is also given as input. Model summary is:

Layer (type) Output Shape Param #
the_input (InputLayer) (None, None, 26) 0
layer_1_conv (Conv1D) (None, None, 30) 3930
conv_batch_norm (BatchNormal (None, None, 30) 120
rnn_bi (GRU) (None, None, 40) 8520
bt_rnn_bi (BatchNormalizatio (None, None, 40) 160
bidirectional_15 (Bidirectio (None, None, 40) 19440
bt_rnn_final (BatchNormaliza (None, None, 40) 160
time_distributed_15 (TimeDis (None, None, 29) 1189
softmax (Activation) (None, None, 29) 0
Total params: 33,519 Trainable params: 33,299 Non-trainable params: 220
None

Optimiser used: Adelta()
loss function: ctc_loss function.
dropout: 0.5

training and validation loss in last epochs is:
Epoch 392/400 27/27 [==============================] - 36s - loss: 19.9499 - val_loss: 16.5945
Epoch 393/400 27/27 [==============================] - 34s - loss: 18.9789 - val_loss: 14.1015
Epoch 394/400 27/27 [==============================] - 36s - loss: 17.9598 - val_loss: 14.2997
Epoch 395/400 27/27 [==============================] - 34s - loss: 17.1506 - val_loss: 15.1215
Epoch 396/400 27/27 [==============================] - 35s - loss: 17.4900 - val_loss: 14.0334
Epoch 397/400 27/27 [==============================] - 35s - loss: 17.7459 - val_loss: 14.7812
Epoch 398/400 27/27 [==============================] - 35s - loss: 18.3460 - val_loss: 14.4461
Epoch 399/400 27/27 [==============================] - 35s - loss: 17.4311 - val_loss: 15.5965
Epoch 400/400 27/27 [==============================] - 35s - loss: 17.6892 - val_loss: 12.4165

Can anybody explain me how this loss is interpreted? What could be the correct values of training loss and validation loss, so my model correctly predicts the output values?

I tried reducing the loss and it did reduce, with difference of plus or minus 1 unit, but test tests were totally incorrect. Can anyone suggest me ways to gain correct test results?

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.