kepstin: I must say, finding differences in those songs is properly hard, even after having the exact times from the matching algorithm :)
2016-03-28 08821, 2016
a7medo778 has quit
2016-03-28 08849, 2016
kepstin
heh, and you don't want to make the matching oversensitive, since that'll make it throw away matches for things that are actually the same :)
2016-03-28 08800, 2016
luks
and the new matching algorithm will depend on <5s segments that are distinct enough to tell those songs apart, so it won't be very robust :)
2016-03-28 08828, 2016
luks
I'm not working with averages over the entire fingerprint this time, so it shouldn't be a problem, I basically split the fingerprints into segments and if there are some segments that do not match well, it will not consider those two fingerprints to form the same "acoustid"
2016-03-28 08814, 2016
Freso
luks: Will there be some kind of versioning so it's possible to tell when generation an AcoustID is?
2016-03-28 08821, 2016
luks
probably not, this won't make it to acoustid for a long time and when it does, it will only affect a very small chunk of the database
2016-03-28 08807, 2016
reosarevok
Clint: paella is from Valencia! :p
2016-03-28 08856, 2016
kepstin
so, it's sort of like it'll do the average matching to find match candidates, then if it's a case where some small segments are very different and the rest is the same, it'll throw away the match?
2016-03-28 08816, 2016
luks
well, it will still give you the match when searching, but it will be more strict about merging individual fingerprints into "acoustids"
2016-03-28 08835, 2016
kepstin
ah, so since it'll keep them separate, you'll get a bunch of acoustids with different match% returned, instead of only one acoustid back?
2016-03-28 08858, 2016
luks
you already get multiple acoustids back with some score
2016-03-28 08858, 2016
kepstin can't really remember the lookup api well, he should take a look at the docs again :)
2016-03-28 08821, 2016
luks
so everything more or less stays the same, except that the internal search when processing a new submission will be more strict
on the second graph, the blue line is an error value for the match, I guess?
2016-03-28 08820, 2016
luks
it's the difference between two levels of "blur" (the blue and green lines in the plot above), it's normally used in CV for blob detection
2016-03-28 08812, 2016
luks
and it's smoother out a bit, to avoid noise around 0
2016-03-28 08816, 2016
luks
smoothed
2016-03-28 08809, 2016
luks
the reason I'm doing this is so that I can tell when two fingerprint start matching, so I can locate a short sample in a long one and stuff like this
2016-03-28 08827, 2016
luks
telling those songs apart is just an added bonus :)
2016-03-28 08832, 2016
kepstin
cool
2016-03-28 08824, 2016
kepstin manually looks up a 'the world is all one' fingerprint out of curiosity - it returns one result only, with a list of multiple musicbrainz recording ids.
2016-03-28 08858, 2016
kepstin
using my awesome application #39, "Kepstin is using curl to manually do lookups on the command line"
2016-03-28 08826, 2016
Leftmost
Is that available on github? Or do you run it as a service? :-P
2016-03-28 08806, 2016
kepstin
it's currently version -2, which I think means you have to use a time machine to obtain a distributed copy.
2016-03-28 08827, 2016
kartikgupta0909 joined the channel
2016-03-28 08853, 2016
krono has quit
2016-03-28 08842, 2016
krono joined the channel
2016-03-28 08852, 2016
Clint
reosarevok: i agree
2016-03-28 08846, 2016
Gilou
are there any protection in abz / acoustic id to avoid clearly wrong music from a bad mbid ? (bad as in, not set to what the song really is)
2016-03-28 08843, 2016
Gilou
not sure how that could work.. but I have seen some weird values at some points, and I assumed it was because something went wrong there, rather than the algorithm being totally fooled.. (I don't have the example handy, hence my asking around a little bit vaguely)
2016-03-28 08839, 2016
Freso
Gilou: No.
2016-03-28 08847, 2016
Freso
Gilou: For AcoustID, you can log in on acoustid.org and de-associate wrong matches.
