stream-audio-fingerprint
stream-audio-fingerprint copied to clipboard
adblockradio
Comparison with https://github.com/acoustid/chromaprint
- What is the fingerprint size of S.A.F. vs Chromaprint?
- How long does it take to discern a match in S.A.F. vs Chromaprint?
- How accurate is S.A.F. vs Chromaprint given the same files?
- Does S.A.F. and Chromaprint work even if there are white noise?
See: https://github.com/acoustid/chromaprint
Fingerprint size / Accuracy / Time to match: All of this depends on the parameters you use to tune the algorithm. It's a tradeoff vs computation burden and size of the fingerprints DB.
If I remember correctly (and Google is your friend) Chromaprint is for perfect match recognition on full tracks, while SAF (aka Shazam or more commonly landmark) works on short snippets with possibly noise (white or not). In return landmark is more CPU intensive, with more output.
PS: it would have been nice if you had written a bit about the context of your request.
@dest4 for reference, these two article gives info on chromaprint
- http://www.ijcset.com/docs/IJCSET17-08-05-021.pdf
- https://oxygene.sk/2011/01/how-does-chromaprint-work/
It turns out that 15 seconds is enough for chromaprint to have a match, but the fingerprint is much lighter (does not seem to say how light, which is why I asked the question). I would like to ask though, what is the average and standard deviation of fingerprint data per second?