search

astorfi / 3D-convolutional-speaker-recognition

:speaker: Deep Learning & 3D Convolutional Neural Networks for Speaker Verification
Apache License 2.0
780 stars 274 forks source link

Dataset for evaluation #19

Closed toshikwa closed 6 years ago

toshikwa commented 6 years ago

Hi Astorfi, I'm trying to train speaker recognition model with your model. Since I'm a beginner at programming, I don't understand your code nicely. For enrollment and evaluation phase, I just have to prepare the data (shape of (sample, 1, 80, 40))?? I read the paper and I don't know if I have to copy the data of single utterance to make the data (shape of (sample, 20, 80, 40)).

Also I prepare the data for development (shape of (97, 20, 80, 40)) using input_feature.py, but do I have to prepare the data (shape of (97, 80, 40, 20))??

Thank you very much.

astorfi commented 6 years ago

"I read the paper and I don't know if I have to copy the data of single utterance to make the data (shape of (sample, 20, 80, 40))": Answer: For evaluation, you need to copy.

"Also I prepare the data for development (shape of (97, 20, 80, 40)) using input_feature.py, but do I have to prepare the data (shape of (97, 80, 40, 20))??" Answer: The shape must be formed as it is mentioned in the paper and/or the default of this repository because the architecture is designed and adapted for the specific shape.