Parameters for CRNN

I'm still having some trouble reconciling the discrepancy between the Arik et al. CRNN paper's claimed number of parameters and the number of parameters in my implementation. I did realize I made an error in specifying which dimension is time vs. frequency when defining the stride/kernel size, and after correcting this, the model went up to ~143k parameters. But, the paper says their model, with the same configuration, has ~229k params.

I've tried everything I can think of to identify the error, but there's nothing in the paper that I've found that indicates the model I've built is missing anything. If any of you have a moment to take a look, another pair of eyes looking at the model would be very helpful.

For reference, the summary is:

For just the encoder piece, contains:

• Single convolutional layer with 32 filters, input is (batch, freq/features, time, channels). Stride is (5, 20), kernel size is (2, 8).
• Output is reshaped to be (batch, time, features), where the features are "i-th feature vector is the concatenation of the i-th columns of all the maps" (from original CRNN paper Shi et al, had a much more useful description of how to reshape!).
• Two Bidirectional GRU layers, 64 hidden units each.

Model: "sequential"
Layer (type)                 Output Shape              Param #   
conv2d (Conv2D)              (None, 18, 17, 32)        3232      
_________________________________________________________________
permute (Permute)            (None, 17, 18, 32)        0         
_________________________________________________________________
reshape (Reshape)            (None, 17, 576)           0         
_________________________________________________________________
bidirectional (Bidirectional (None, 17, 64)            117120    
_________________________________________________________________
bidirectional_1 (Bidirection (None, 64)                18816     
Total params: 139,168
Trainable params: 139,168
Non-trainable params: 0

Detect piece:

• Single fully-connected layer, 64 hidden units.
• Sigmoidal layer for output.

_________________________________________________________________
Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense (Dense)                (None, 64)                4160      
_________________________________________________________________
dropout (Dropout)            (None, 64)                0         
_________________________________________________________________
dense_1 (Dense)              (None, 1)                 65        
=================================================================
Total params: 4,225
Trainable params: 4,225
Non-trainable params: 0

All together:

Model: "arik_crnn"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
sequential (Sequential)      (None, 64)                139168    
_________________________________________________________________
sequential_1 (Sequential)    (None, 1)                 4225      
=================================================================
Total params: 143,393
Trainable params: 143,393
Non-trainable params: 0

I ended up shooting an email to the author in hopes he could provide more details on the architecture than are in the paper. Will post here if I hear back!