Hacker News Reader

Comment by unltd | Hacker News Reader

Great Job !

Could you describe the usecases ? Is it for mixtapes uploaded on youtube by DJs, or Over-The-Air recognition in music festival videos ?

Because Music ( single tracks ) uploaded on youtube is usually already identified so it could be found.

View on HN

One of the most common comments on YT videos I see are people asking for the name of the song used in a video.

Yes, is one of the archetypical creatures of internet. I bet that 99% of those people are lawyers... or maybe the author of the song.

Music used in compilations, ads, intros etc are typical usecases. Mixtapes & livesets of course are also great. But when pitch/bpms have been altered more than 1-2% we currently get a lot of false positives. We are still working on finding a solution to this.

I think I've read on the echonest board that the most common solution is to index multiple pitch variants of the same songs. Apparently that's what Shazam does.

Also the guys from Trax-air.com are doing something pretty similar to you guys but with pitch/bpm bending support.

So far we've been hesitant to go that route as the current 7m fingerprints come down to 42m+ documents in Lucene. I.e. If we were to save 20 versions of each fingerprint in different bpms we'd quickly have about a billion+ documents on our hands to be searched on every query (with ~1000-2000 hashes per document)

I was thinking about this too but read before that the echonest fingerprinting doesn't handle pitch changes like Shazam.

Would be interested to know if you figured a way around that!

Mix tapes is an ideal use case.

Reply on news.ycombinator.com