I am trying to implement a spoken language identifier from audio files, using Neural Network. I need to generate one feature vector for each audio file.

From what I have read the best features (for my purpose) to extract from the a .wav audio file are the MFCC.

Does anyone know of a Python code that does such a thing?

  • 1
    $\begingroup$ Your question is too broad. We can't really just explain how to pick an appropriate feature extractor without writing a couple thousand lines of code or writing a textbook on speech recognition. That's exactly what I'd recommend here: read a textbook on classical speech recognition. And instead of the classical classificators, you plug in DNNs. $\endgroup$ Jan 3, 2017 at 12:06
  • $\begingroup$ use python_speech_features; a library to extract features from sounds; look for it on github $\endgroup$
    – Anonymous
    Jul 13, 2018 at 20:59

1 Answer 1


Have a look at these two python libraries that provide a number of audio features easily from WAV files, including MFCC.

Good luck!


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.