#metabrainz

/

      • reg[m] has quit
      • texke` joined the channel
      • texke has quit
      • gcrkrause3 has quit
      • gcrkrause3 joined the channel
      • BrainzGit
        [musicbrainz-server] 14mwiencek opened pull request #2394 (03master…prod-access-log-middleware): Enable Plack::Middleware::AccessLog in production https://github.com/metabrainz/musicbrainz-serve...
      • reg[m] joined the channel
      • akshaaatt
        Hi bitmap! I was planning to have the design system hosted on something like design.metabrainz.org and required help with that setup
      • TOPIC: MetaBrainz Community and Development channel | MusicBrainz non-development: #musicbrainz | BookBrainz: #bookbrainz | Channel is logged; see https://musicbrainz.org/doc/IRC for details | Agenda: Reviews, Doc sprint (yvanzo), Repo review (reo)
      • BrainzGit
        [design-system] 14akshaaatt closed pull request #49 (03master…chromatic-ci): Publish on Chromatic https://github.com/metabrainz/design-system/pul...
      • reosarevok
      • BrainzGit
        [musicbrainz-server] 14reosarevok merged pull request #2390 (03master…remove-coc-file): Delete CODE_OF_CONDUCT.md and use org default https://github.com/metabrainz/musicbrainz-serve...
      • lucifer
        reosarevok: oh lol 🥲
      • yvanzo
        O’Moin
      • reosarevok
        moin!
      • yvanzo: before I start writing it, we don't have any docs for how to add support for a new URL domain to the code, right?
      • As in, a doc that explains what files to change for autoselect/cleanup, favicons, sidebar, etc
      • yvanzo
        reosarevok: No, we should even probably have a separate doc explaining how to handle those tickets to check current usage in the DB, old and current links on the web…
      • Like HACKING-URLCLEANUP.md?
      • reosarevok
        Hmm, I was going to put it on HACKING but that also seems good
      • We can move it to a dev docs repo if we eventually start one
      • yvanzo
        Sure :)
      • reosarevok
        So maybe have a heading in HACKING like
      • And then write the doc in that file
      • yvanzo
        Yes, the same as Cover Art Archive development
      • reosarevok
        Ok :)
      • yvanzo
        Btw, maybe just HACKING-URL.md if it is not limited to cleanup.
      • reosarevok
        Yeah, fair
      • Shubh joined the channel
      • mayhem
        moooin!
      • alastairp
        those headers are great, lucifer! https://usercontent.irccloud-cdn.com/file/NeRzI...
      • lucifer
        indeed! :D
      • i saw those in RTD tutorial first and thought to add LB docs as well.
      • alastairp
        why do we have "Web root url" in the api docs? I can't see it used anywhere in the docs
      • lucifer
        yeah, i think we can remove that. dosen't make sense to list non-api endpoints there in LB API docs.
      • mayhem
        alastairp: got a sec for some brainstorming?
      • alastairp
        yes, go for it
      • lucifer
        although it could come in handy in dev/maintainer docs
      • mayhem
        let me find a reference real quick. hang on.
      • alastairp
        lucifer: yeah, there may be value in having it somewhere, but it feels a bit out of place right there
      • lucifer
        yup makes sense. i'll remove that in another PR. the current ones depend on each other so making the change here will cause cascading merges/rebases to resolve conflict.
      • alastairp
        no prob
      • akshaaatt
        lucifer, A reminder about the data safety form in playstore 😃
      • mayhem
        meh. can't find the paper that talks about moods derived from listens. but that paper said something along the lines of:
      • "Extrating moods from audio is hard and doesn't work that well".
      • *extracting
      • alastairp
        the one I linked last week?
      • mayhem
        yes.
      • and in general, there is a sentiment that user behaviour is a better input to recommendation that audio files.
      • A point that Dimi made in this defense.
      • so, then it seems that AB is really barking up the wrong tree.
      • not only does it not provide good results, its also very hard to do unless you have access to a huge cache of files. Easy for spotify, very hard for us.
      • alastairp
        yeah, the question of "can you throw machine learning at audio signals and get some results?" has always been uncertain
      • mayhem
        And I think that we fell in love with the concept; we were never fully clear on what data we wanted to collect, and we just got ourselves hornswaggled on this approach. I think it its time to step back even further than we already have and re-examine.
      • exactly. so, how about we don't. period.
      • instead, lets us ask ourselves: what data do we want to collect?
      • once we answer that, we should find ways to collect those pieces of data, by the easiest means possible. meaning: what approaches fit with an open source approach.
      • alastairp
        so, instead of "description of songs based on analysing audio", maybe we actually just want "description of songs"
      • lucifer
        akshaaatt: thanks for the reminder, lets talk with mayhem about that after this conversation.
      • mayhem
        DING! EXACTLY THAY!
      • THAT
      • because reading the moods from behaviour paper gives a clear insight. If transferlearning is needed -- well, we have a CF filtering setup already. If we're bolting another piece of on top of that, then this may not be that much work in the grand scheme of things.
      • right now AB needs: DSP and ML knoweldge.
      • the new approach only needs ML knowledge. and everyone wants to do this right now -- its the hot thing to be doing.
      • alastairp
        -> https://arxiv.org/pdf/2010.11512.pdf link if you had lost it
      • mayhem
        and we have the infrastructure for it already. so, lets use that.
      • thanks!
      • there are bits and pieces of AB that are clearly useful. such as creating datasets, managing them and then throwing them at ML.
      • newAB could then throw away all the audio stuff and keep all the ML/dataset stuff.
      • alastairp
        yes, right
      • mayhem
        we could start with collecting mood information manually from users as part of BrainzPlayer. (listen to a track, select the mood from a dropdown, submit to newAB.
      • once we have a body of those, we can start doing the ML as described in the paper. the paper allows us to "fill in the blanks" of the data we're missing.
      • with me so far?
      • alastairp
        oh, that's interesting
      • working out how to collect data has always been a bit of an open question
      • mayhem
        and those are our strengths OR are things that are tangibly close to being within our reach.
      • alastairp
        and I think that the AB way of saying "here are some results, do they look wrong? give us feedback" was a bit weak because the data was a bit sparse
      • mayhem
        so, lets focus on that. lets build an OpenML project with a focus on music.
      • yes, indeed.
      • alastairp
        but maybe integrating into BP might be a better way of getting that data
      • the previous way that we've done it is give it to students as an assignment. "your task is to listen to these 500 songs from jamendo and categorise genre/mood/other things, then do some analysis on the results"
      • mayhem
        I think BP is the outlier on this front. I think with enough effort, we can do music analysis on it. I think you're close to showing that.
      • but, just to get BPM, do we really need to build all this infra for it?
      • what if we wrote BPM stuff as a pluging for picard?
      • and picard runs 3+ algs and if there is consensus, submit the data.
      • bam, we're done.
      • alastairp
        how do you mean? people use picard and tap along with the song?
      • oh, for the algorithms. mmm
      • one sec, let me commit some stuff
      • mayhem
        yes. since it looks like there are promising algs, lets stuff them into picard and be done on that front.
      • then focus ML in the newAB and I think we have a project might might get more people interested in helping.
      • mayhem wonders if lucifer has any ideas
      • monkey
        Are "moods" a specific subset of tags?
      • lucifer
        nothing to add but following along the discussion. +1 on all BP, picard and new AB ideas
      • monkey
        (I've been wanting to add a tags input and display into the ListenCard on LB, perhaps another input can prompt for adding/selecting moods)
      • zas
        legoktm[m]: ping
      • mayhem
        monkey: moods could be tags -- yes, but I think I would build a more general infrastructure to support this in newAB.
      • The only thing that bugs me about this is that newAB no longer deals with acoustics. thus the name is now borked.
      • alastairp
        yeah, that's more like music-dataset-brainz
      • https://github.com/metabrainz/mir-analysis/blob... I did this at the end of last week
      • some odd results still in 04 - Pink Floyd - Wish You Were Here.flac and 03 - Miles Davis - Blue in Green.flac
      • mayhem
        wish you were here is also a tough candidate for this shit.
      • monkey
        Seems like a consensus approach would give pretty reliable results
      • alastairp
        yeah, I realised that pink floyd and miles davis probably aren't the easiest candidate set
      • mayhem
        there is consensus, but is shine on 140bpm??
      • that seems too fast to me.
      • I guess spotify agrees with it.
      • well tempocnn and madmom seem like easy candidates to toss out.
      • alastairp
        shine on is interesting because the parts are really different
      • mayhem
        yerp
      • alastairp
        there are some slower parts (60ish), and some really fast parts too
      • mayhem
        lol @ blue and green. Not 170BPM. collective fail.
      • alastairp
        and so you have to start thinking if you want to do a single bpm or measure how it changes over the whole song
      • mayhem
        I guess we're tying to find "representative BPM", not actual BPM.
      • because actual BPM is... variable over the song.
      • but for a lot of use cases that we're chasing after, that doesn't matter.
      • alastairp
        but averaging all of the BPM values over the duration of the song isn't great either, because you end up with none of them
      • for the 1 queen song, I plotted bpm for most of the algorithms: https://github.com/metabrainz/mir-analysis/blob...
      • mayhem
        yeah, that wasn't necessarily my suggestion though.
      • alastairp
        that track seems kind of stable
      • oh sure - that's not the only way of doing it
      • mayhem
        I think if we define BPM as "the BPM of the most 'recognizable portion of the song" then we narrow the scope of the problem.
      • we make the problem more human.
      • and we have humans.
      • what if we had this workfow:
      • 1. User runs automatic BPM detection that is tuned to only accept the clearest results.
      • 2. If there is clear consensus, we're done.
      • BrainzGit
        [bookbrainz-site] 14MonkeyDo merged pull request #754 (03master…collectionPageNameSection): fix(CollectionPage): Added Horizontal rule in CollectionPage https://github.com/metabrainz/bookbrainz-site/p...
      • mayhem
        3. If there is not, have the user select the most "salient" parts of the song. and then run analysis again. do we get a stable result now? if so, we're done.
      • 4. If not... not sure. "tap on every downbeat" and we'll calculate it?
      • alastairp
        within something like picard? BP?
      • mayhem
      • alastairp: both, ideally.
      • alastairp
        I like the idea of "indicate to us what you think the most representative part of this song is"
      • mayhem
        MLBrainz would also work great for building candidate sets for music recommendations.
      • yes, coupled with loads of users doing this, we can gather the best data out there.
      • alastairp
        the trick is to convince users that it's worth their time to help with this
      • mayhem
        that hasn't been a problem for us in the past.
      • I think the key is to make it easy enough for them to do it. Adding "calls to action" to BP has been on the wishlist for a while.
      • I would like to see all sorts of things there:
      • 1. This artist has no patronage link. Do you know of one?
      • 2. This track has no BPM, would you like to help us submit it?
      • 3. This track has no genre tags: We think it might be these tags. click a tag or enter new tags.
      • BrainzGit
        [musicbrainz-server] 14reosarevok opened pull request #2395 (03master…document-url-in-hacking): Document URL support in MBS https://github.com/metabrainz/musicbrainz-serve...
      • alastairp
        BPM on BP is interesting. tap along is something that we could get users to do
      • but I'm also wondering about js-based algorithms + using the stream as the user is listening to the track
      • mayhem
        having access to the audio is the trick. I doubt that is even possible in most cases, unless we are doing it for a local file.