The article's headline isn't well backed up by the article. The article more claims that advantages that men have in other sports are erased in ultra-endurance sport, leveling the playing field.
The headline question is only really addressed by the combination of two things in the article (the second being brought up much later, and you kind of have to connect the dots yourself a bit): 1/ women have begun setting records in endurance sports 2/ women constitute a minority of participants in such events.
The first point, beginning to win some records, doesn't by itself address the question of the headline. But taken together with the relative rarity of women they say participate could point to there being some evidence for "better than" vs "equal to." Or it could be that for the records won, the winners are truly exceptional.
Whatever that rule about headlines ending with a question mark notwithstanding, I always cringe a little at headlines like these that seem to wish for a conclusion that's not really the direction of the article.
I recently bought a tablet for sheet music, mostly to replace a stack of jazz "Real Books" at jam sessions. And the phone camera scans I made are okay, but fixed in size and have a lot of artifacts. And it would be great to transpose on the fly for e.g. Bb or Eb instruments, but being a scan this is obviously not possible.
I got digging into the state of optical music recognition and came away concluding that music is basically a greenfield for AI wherever you look. Optical music recognition is pretty terrible. AI understanding of music theory is terrible (actually looking at music that is; LLMs do okay at text descriptions of theory concepts where you can imagine some online texts making it in).
I think the issue is that we still don't have great digital formats that encode the dots on paper that musicians read. Music notation is pretty rich. Midi doesn't capture all of what's needed for symbolic understanding, because it was mostly made for capturing aspects relevant for playback or performance. MusicXML seems to be the closest for a digital format that encodes the information a musician would want, but there aren't great corpora of training data that would connect a MusicXML representation to sheet music images or to audio. I think that's because MusicXML falls short of encoding enough information to engrave music. Tools like MuseScore need to track a bunch of layout information that isn't encodable in MusicXML. Lilypond format is less verbose that MusicXML and contains a bit more information that is useful to the score creators, but most people don't create sheet music in lilypond. (As an aside, Lilypond bums me out with the state of jazz fonts. I hate looking at "legit" scores in jazz context)
I realize this is mildly off topic, but every time I see people making incremental gains on OCR, which to my mind is pretty good, I am reminded of how abysmal OMR is.
So, the format for musicologist and researcher in music is the MEI format: https://music-encoding.org/ for which the reference engraver is verovio: https://www.verovio.org/index.xhtml
Note that verovio is able to engrave in svg format while keeping a maximum of information from the original mei score, meaning that you can extract enough metadata to create an actual detection dataset for a deep learning model.
This is my horrible hacked up script that will create a coco dataset from a set of scores engraved with verovio: https://github.com/kwon-young/music/blob/main/svg2pl.py
I have published a synthetic music score dataset from this: https://www.kaggle.com/datasets/kwonyoungchoi/trompa-coco/da...
I anyone wants to try and fit a detector on top is welcome :)
To understand why OMR is so neglected is because most people widely underestimate the difficulty of the task.
It has a specific blend of the most extreme shapes combined with an extremely complicated graphical grammar...
Thank you for this! Both MEI format and the Verovio engraver are news to me. I will check them out.
My first thought was whether MEI format is being added to MuseScore (the sheet music editor I use these days). It looks like it is: https://music-encoding.org/musescore-doc/
As a somewhat related aside, now that the MuseScore people own Hal Leonard and seem to pushing integration with their cloud subscription service, I wonder if they'll see some of these directions as potentially competing with them. I don't think there's anyone who wouldn't love a transposable clean digital version of their Real Books... and if Hal Leonard is in the business of selling Real Books, I can see where good OMR might be a problem for them. I guess piracy of scanned versions is already rampant, so maybe it's a wash.
> music is basically a greenfield for AI wherever you look
AIN'T THAT THE TRUTH.
My girlfriend is studying musicology and she has some physical disabilities that make it difficult for her to write things down sometimes. So I try to help her by writing some AI-powered TTS/OCR/etc. apps here and there. It becomes painfully obvious that music was never considered an important part of any AI training dataset, anywhere.
These days, I'm pleasantly surprised by how well Opus 4.8 understands/explains music theory (as you said). But ask him to transcribe/OCR/OMR some sheet music and he'll confidently give you the MusicXML/Lilypond equivalent of "2 + 2 = horse".
I really hope this ignored area will be swept up with the rest of the rising AI wave, but it's still criminally undervalued.
> how well Opus 4.8 understands [...] and he'll confidently
I always think of the nun character against AI in Mrs Davis:
> "Don't give it a name. No one calls Facebook Doug. No one calls Twitter Mary Lou. No one calls them anything, because no one uses them anymore. They use it, and it's not a person. It's code. - Mrs Davis
You're not wrong, but if I'm talking to a Chinese Room, I'm still going to use pronouns and all sorts of meatbag-specific language. It doesn't matter if there really is a real person on the other end or not -- it's easier for me to just default to the assumption that there is. Monkey brain gonna anthropomorphize.
On the other hand if I try to talk to Facebook, all he says in response is "200 OK".
Eh, humans give names to and/or anthropomorphise lots of things. My partner names all of her cars and bikes; I don't. Isn't it more rational to feel some sort of connection and anthropomorphise a tool with which you can at least have an intelligent conversation, than a simple machine?
I recently left a job at where I was working with open data producers / providers across a lot of domains. A lot of data is produced and released for free by governments and nonprofits because it's either directly part of the mission, or it's a natural byproduct of the organization's mission. Occasionally, you'd have really great datasets come out of industry / commercial organizations because the data were a byproduct and didn't create a scenario where a data release would create opportunity for competition.
I've been thinking about what kind of organization could be self-sustaining and also produce good music AI training data as a natural byproduct. An ideal arrangement would be something that provided some incentive or benefit to musicians in exchange for their recorded interpretation of sheet music. Soundslice, mentioned by another user, seems to do that. They let both teachers and students upload recordings of music that has been turned into MusicXML. The recordings, paired to those snippets of sheet music, has to be a gold mine. Assuming they have enough users. If they aren't already working on stem separation and automatic transcription, they probably should be. Still, my hope would be to figure out some kind of sustainable model where that dataset could be created and released for open model development...
As a domain, I see AI in music as a boon to human creativity. I am very much a novice jazz improvisor, and a passable amateur technician on the trombone. Human instructors can do a lot for me, but there's a lot that is "grinding it out" repetition, where I think AI could be a huge aid. I heard Sam Harris on a podcast recently talk about his bullishness on the humanities (paraphrasing: people don't care if a human reads their MRI if detection is good, but people probably do care that a human wrote the novel they're reading).
Music might even be a better example of the irreplaceability of people. While some people might bop along to a tune composed by Suno on the radio, live music is just so much more enjoyable for me. And even better than listening to a live show played by masters, is playing together with friends. To the extent that AI can patiently help us learn the skills to express our own creativity, I'm here for it!
I forgot to mention ABC. I have seen a few LLMs look at that. There was a model / paper published a couple years back called ChatMusician that built around it.
With the caveat that I'm not terribly fluent in ABC, it seems to me that simple things are simple, but hard things seem to be nearly pathological. And (again, maybe a lapse in my understanding) it seems like there may be a fair number of concepts that are impossible to convey in ABC?
Lastly, if I understand correctly, ABC got its start and is mostly popular as a simplified format for church songbooks. I'd imagine that would, uh, influence the training corpora towards sounding a bit... church songbooky.
EDIT: I may have been overly dismissive of ABC on first glance. It does seem like people have extended it quite a bit, and that it's at least, in theory, capable of encoding most of what I'd expect. And it's human readable, which is a benefit. Though, readability does take a stiff penalty the more richness you add (e.g. dynamics, articulations, stacked notes, etc)
ABC was originally designed for European folk music [0], not church music. The corpora as a result is largely fiddle tunes, particularly Irish (see for example https://thesession.org).
ABC started very simple, because most of the performance information for folk music isn't written down, it's inferred by the player according to the idiom of that particular tradition. As usage of ABC has grown it's gotten more powerful but still falls far short of formats designed for western classical, like MusicXML or Lilypond.
To let LLMs compose music I chose json for context efficiency, but this seems like it could be better choice, simple, efficient, already a real format.
For just chord analysis, there's "Harte notation", which is meant to be unambiguous representation of the notes (https://ismir2005.ismir.net/proceedings/1080.pdf). That obviously doesn't get you all of the additional information necessary for engraving and full representation of the music, but there are research datasets available using it like https://github.com/smashub/choco. I've also used the https://github.com/MarkGotham/When-in-Rome dataset for some analysis work, but again that's not 100% what you're looking for.
You might like the "iReal Pro" app for the replacement and transposition of jazz standards on your tablet. It's pretty great for that use case versus camera scans.
I observe that music OCR space and the only really good solution so far is soundslice. You scan and review some edge cases and get really good results. Paid service by a small company, very worthy to be supported!
I just signed up a trial, and uploaded a messy Real Book scan. It did very well! It missed the coda markings, but then again the directive in the Real Book was nonstandard. I guess that's a case where a multimodal model might have been able to read the text ("after solos, D.C. al coda") and do something smarter.
I'd imagine that rendered audio that just used midi voices (even high quality "Real Instruments" midi voices) would be pretty brittle for e.g. stem separation or automatic transcription. In a best case, I think you'd start with a clean digital representation, render sheet music imagery, and then have lots of recordings by a bunch of real instrumentalists playing the same music.
On the topic of stem separation, I've wondered about creating a quasi-synthetic dataset by taking chunks of recordings by real musicians playing them back in a real space in various combinations and recording the resulting analog-blended cacophony. Could repeat in various environments like cathedrals, basement bars, etc for realism :-)
It's just an entrenched aesthetic preference. Jazz fonts (fonts in this context refers both to the words and the music symbols) tend to be quite heavy with thick lines. I've heard that the thick hand-written style was originally to make charts more readable in dimly lit clubs, but with tablets and such, that's an anachronism now.
You can look at samples of Hal Leonard's Real Book(s) on their website to get a sense of what it looks like. Again, just an aesthetic preference, but one I and many others hold nonetheless.
I also don't love the conventional handwritten aesthetic you often see for jazz fonts. For a project I've been working on, I ended up pulling the handful of chord symbol glyphs out of MuseScore's Leland Text font and adjusting them for use in the UI since I couldn't find a suitable option out there.
...but why is it so complicated? A novice interpretation of "music" is "a bunch of notes!" ... my amateur interpretation of "music" is "layers of notes".
You can either spam 100 notes in a row, or you effectively end up with:
melody = [ a, b, [c+d], e, ... ]
bassline = [ b, _, b, _, ... ]
music = melody + bassline
score = [
"a bunch of helper text",
+ melody,
+ bassline,
+ page_size, etc...
]
...so Lilypond basically made "Tex4Music", and the format serves a few dual purposes...[snip]
Everyone I know who is a casual jazz musician / student uses iReal Pro for practicing soloing. It does an okay job. The styles are mediocre and mechanical, and not as good as Band-in-a-Box or as rich as JJazzLab with its ability to plug in Yamaha styles.
I also own 4 editions of a new entrant called "Quartet" that uses carefully recorded, individually tracked, time annotated recordings of jazz standards by a real band. Solo sections can be repeated an arbitrary number of times and within fairly constrained limits tunes can be transposed, sped up, or slowed down. Of course the more you stretch or pitch bend the recordings, the more it sounds like garbage.
Something like iReal Pro, where you can key in your chord changes, configure repeats, specify instrumentation, etc. but generate high quality backing would be almost a holy grail for musicians' solo practice.
I also imagine this kind of thing would be a near perfect case to demonstrate "neurosymbolic AI". Backing tracks are constrained by actual constraints, not vibes. Suno does some impressive things, but was useless in my experience for trying to create a backing track.
"iReal, but with AI-generated backing band" is an idea I've even considered trying to build, but honestly I'd be just as happy to buy this app (or contribute to an open source version). Someone build this!
Most instruments tend to pitch sharp or flat depending on the partial. I don't recall any music teachers giving advice that specific positions should routinely get adjustments, but instead that notes in a particular partial should be adjusted. For example, F above middle C should be flattened when played in 1st position to compensate for 6th partial tending sharp. Or the G in 2nd position above that F needing to be pulled in a bit to compensate for 7th partial tending flat.
Manufacturers have different philosophies around this as well. I have a vintage mid-1960s King 3b whose partials line up differently and require different adjustment from my modern XO 1634... and both of those horns are extremely similar .508 bore tenor trombones.
I like how you say 6th partial is "tending sharp" and 7th partial is "tending flat", like they're comparable. I don't know about your horn, but on every one I've played that 6th partial is pretty close but the 7th partial is so far out that we refer to positions on the 7th as half positions. Euphoniums don't even play the 7th partial because it's so far off. They'll play the F# and G from 8th partial.
(Didn't mean to imply you didn't know that, I just was humored by you using the same term for both).
That advice makes more sense according to my understanding of the physics -- the entire partial might be slightly off and every position in the partial should be adjusted similarly.
The just/equal temperament thing lead me to suspect that it was the 5th partial (a major 3rd partial, the D) that would be the one most likely to be off, but a trombone is neither a perfect cylinder nor a perfect cone so simplified models might be off. The perfect 5th (aka both the F partials) is pretty exact on an ideal model, but a real trombone isn't ideal.
Curious what you're looking for in that position as the aperture for what DS do at AWS is quite broad (my current role). DM me if you want to chat—contact info in profile.
If you buy their brushless line, you can add a few decent tools to your lineup while using the cheap stuff for everything else. Same battery platform generally. I have a lot of their cheap stuff, plus a few good ones that see more use.
That would suck, because even the same company might have 2 or more different battery platforms. I, for one, have Milwaukee tools from both M12 and M18 platforms. They are for different applications and I specifically bought some M12 tools because their M18 equivalent was too big for my applications, and, on the other hand, I bought some tools in M18 because their M12 counterparts were underpowered for my applications. Imagine running a driver to assemble your PC and an SDS MAX hammer off the same battery?
When I watched Incubus I remember him sounding very much like he was trying to speak Italian. My only basis for comparison are some podcasts in Esperanto I've listened to, and completion of the duolingo course (I've forgotten everything).
I worry about the Slate truck being DOA with expiration of incentives for EVs. Someone please tell me I'm wrong, because if they do deliver as promised, I'll be excited to buy one.
For me, I'm hoping it fills the mid-90s Isuzu Pup sized hole in my heart.
From the papers I've read, the stem separation models all seem to train off what seems like a fairly small dataset that doesn't have great instrument representation.
I wonder if you could assemble a big corpus of individual solo instruments, then permute a cacophonous mix of them. IIRC the main training dataset is comprised of a limited number of real songs. But I think a model trained on real songs might struggle with more "out there" harmonies and mixes.
The headline question is only really addressed by the combination of two things in the article (the second being brought up much later, and you kind of have to connect the dots yourself a bit): 1/ women have begun setting records in endurance sports 2/ women constitute a minority of participants in such events.
The first point, beginning to win some records, doesn't by itself address the question of the headline. But taken together with the relative rarity of women they say participate could point to there being some evidence for "better than" vs "equal to." Or it could be that for the records won, the winners are truly exceptional.
Whatever that rule about headlines ending with a question mark notwithstanding, I always cringe a little at headlines like these that seem to wish for a conclusion that's not really the direction of the article.
reply