Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Comparison with https://github.com/acoustid/chromaprint #15

Open
DonaldTsang opened this issue Feb 27, 2019 · 2 comments
Open

Comparison with https://github.com/acoustid/chromaprint #15

DonaldTsang opened this issue Feb 27, 2019 · 2 comments

Comments

@DonaldTsang
Copy link

DonaldTsang commented Feb 27, 2019

  1. What is the fingerprint size of S.A.F. vs Chromaprint?
  2. How long does it take to discern a match in S.A.F. vs Chromaprint?
  3. How accurate is S.A.F. vs Chromaprint given the same files?
  4. Does S.A.F. and Chromaprint work even if there are white noise?

See: https://github.com/acoustid/chromaprint

@dest4
Copy link
Member

dest4 commented Mar 8, 2019

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.

@DonaldTsang
Copy link
Author

DonaldTsang commented Mar 9, 2019

@dest4 for reference, these two article gives info on chromaprint

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?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants