Within a large audio file, I would like to identify sounds that are similar to or identical with exemplary sounds that are used as queries.

I basically need a filter which is defined by one or a few examples.

Any help much appreciated.

  • 1
    This is a job for an intern or tape-op with a pad & pen, not AI.
    – Tetsujin
    Aug 18, 2020 at 15:42
  • Thank you for the comment. I don't expect machine learning to be the only solution. I believe that even a simple rule based on standard deviations should do the trick.
    – VGF
    Aug 18, 2020 at 15:48
  • 1
    If you need 'code' for a computational rule, you might do better in dsp.stackexchange.com - they do that kind of thing over there. We push faders & put mics in the right place ;-) Wish you luck.
    – Tetsujin
    Aug 18, 2020 at 16:21
  • 1
    If I remember my "signal processing" classes from about 10 years ago, what you are trying to do is, well, signal processing. I think you need a "convolution function", and most likely a Fourier Transform. In other words : you need a mathematician.
    – Lucien
    Aug 19, 2020 at 8:20


Your Answer

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

Browse other questions tagged or ask your own question.