Comparing short audio files
galarlo opened this issue · comments
Hi,
I'm interested in finding near-duplicate audio files. My dataset is about 3000 thousands short audio files, between 0.5 seconds to 5 seconds. Unlike Shazam, both the "target" audio (i.e. the songs in Shazam's case) and the user input are short, and both might contain noise.
Can this library help?
If so, are there any recommendations for tuning parameters?
N.B - if a file is matched to multiple other files, it's fine - I have a less efficient algorithm that can verify which match is correct. In other words, I can handle some amount of false positives, but I don't want false negatives.
Sounds like it could be a good use case, but I think you'd be better off just implementing it yourself based on the academic paper linked in the README if possible; I never had much luck getting this implementation to work with much precision and looking over my code, it's kind of a mess (I was still in school). Sorry I can't be of more help!