We have several audio tracks, all of which are different versions of the same track under one type of distortion: the speed of the track is increased by a constant factor K (hence frequences are multiplied by K, timesteps are divided by K), K is relatively small (0.8< K < 1.2).

I want to know the best way to get a good spectrogram out of these tracks. Before defining what I mean by 'good', let me state my final goal: I want to retrieve points, à la Shazam, based on the maximum amplitudes (ie amplitudes > a certain threshold). A good threshold is to be defined too, but I was thinking of taking the average local RMS of the signal and its standard deviation and make the treshold = mean(localRMS) + (constant factor)*std(localRMS). Then I'd like to apply computer vision algorithms to the resulting image to measure similarity.

A good spectrogram is then defined as such:

  1. the frequencies are logarithmically spaced the points of interest

  2. for one track are a translation along the frequency axis of the points of interest of another track.

Do you know what type of spectrogram would be the best? (I'm thinking of using either a logarithmically spaced fourier transform or a constant Q Fourier transform) Would my threshold work or are there better ones? Any remark on the whole design would be truly appreciated.

  • 1
    $\begingroup$ This is a complex topic. I won't try to offer a complete answer, but it seems a constant Q transform is what you are asking for. You will have to experiment with window sizes to align things the way you want in the spectrogram. I would leave the thresholding to post processing or perhaps even incorporate that into the "visual" recognition system. BTW - There may be more direct ways to compare audio tracks than applying computer vision to 2D transforms of you're music. You may want to look into how speech recognition is achieved to inspire other approaches. $\endgroup$ – user2718 Apr 6 '13 at 18:40
  • 1
    $\begingroup$ BTW-There is a shareware program you can use to test out some of the ideas you mentioned in you're post. Check out this site sonicvisualiser.org and links from that site to work others are doing on music analysis. $\endgroup$ – user2718 Apr 6 '13 at 18:52

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.