search

egrinstein / neural_srp

The Neural-SRP method for DOA estimation
13 stars 3 forks source link

Questions bout the feature shape transform during normalization #1

Closed Xiao-xiaohei closed 6 months ago

Xiao-xiaohei commented 7 months ago

Hello, after reading your code, i have some questions:

In GccExtractor, the feat matric shape is

gcc_feat = np.zeros((nb_frames, self._nb_bins, n_output_channels)) gcc_feat = gcc_feat.transpose((0, 2, 1))

and, in Preprocessor::extract_all_feature, the feat is trans to

        feat = self._gcc_extractor(audio_in)
        nb_frames = feat.shape[1]
        feat = feat.transpose((0, 2, 1)).reshape((nb_frames, -1))

which not make sense. ( i mean, the nb_frames refers to different meanings

I can't get it, could u help me about it ？ If there is something wrong in this version of code? Thanks!!!

egrinstein commented 7 months ago

Hi,

Thank you very much for pointing this out. You are correct. I just pushed a fix to this.

Best regards,

Eric