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.
4
-
1This is a job for an intern or tape-op with a pad & pen, not AI.– TetsujinCommented 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.– VGFCommented Aug 18, 2020 at 15:48
-
1If 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.– TetsujinCommented Aug 18, 2020 at 16:21
-
1If 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.– LucienCommented Aug 19, 2020 at 8:20
Add a comment
|