- Видео 70
- Просмотров 67 885
Bob Sturm
Швеция
Добавлен 16 янв 2007
Видео
Artifact 97: "'round and 'round" (traditional) - six settings
Просмотров 22Месяц назад
Trigger warning: The song deals with death and suicide. More information: tunesfromtheaifrontiers.wordpress.com/2024/05/17/artifact-97-round-and-round-traditional-six-settings-sturmudiosturm/
"Stonks Go Up" by Stonky Stonks
Просмотров 155 месяцев назад
Created with Boomy.com March 23 2023. It was distributed by Boomy for a few months, and appeared on RUclips and Spotify, but has been removed by these services for reasons that are unknown.
Artifact 96: Aus einem Text von Ernst Toch
Просмотров 467 месяцев назад
Assembled from many music audio excerpts generated by suno.ai with a text by Ernst Toch. More information: tunesfromtheaifrontiers.wordpress.com/2023/12/25/artifact-96-aus-einem-text-von-ernst-toch-sturm-suno-ai/
Shane sings five octaves with some help from neural synthesis
Просмотров 1922 года назад
Created using neural instrument cloning. More information: erlj.notion.site/Neural-Instrument-Cloning-from-very-few-samples-2cf41d8b630842ee8c7eb55036a1bfd6
Portland Ruth
Просмотров 1182 года назад
Created with neural instrument cloning. More information erlj.notion.site/Neural-Instrument-Cloning-from-very-few-samples-2cf41d8b630842ee8c7eb55036a1bfd6
Perversions (study)
Просмотров 432 года назад
Neural Music Instrument Cloning erlj.notion.site/Neural-Instrument-Cloning-from-very-few-samples-2cf41d8b630842ee8c7eb55036a1bfd6
Audition Preparation
Просмотров 562 года назад
French horn focus, but applicable to other instruments. More information: erlj.notion.site/Neural-Instrument-Cloning-from-very-few-samples-2cf41d8b630842ee8c7eb55036a1bfd6
Speed that plough! TOTM January 2022
Просмотров 952 года назад
Tune of the month at Melodeon.net Jan. 2022 (forum.melodeon.net/index.php/topic,27826.0.html).
Two tunes on the Fonserannes Staircase
Просмотров 262 года назад
I play Sally Gardens and The Banshee, two classic reels.
Introducing: Bosca Dubh
Просмотров 873 года назад
This was a club accordion but I have redesigned it to be a D/G accordion that can play traditional ornamentation in Irish traditional music. The accordion also has a "circus setting". Tunes I play: Boil the Breakfast Early, The Old Pigeon on the Gate, a slide named Denis Murphy's, Sally Gardens in D and G, and Cooley's. More detailed information on the accordion: highnoongmt.wordpress.com/2020/...
Why are you and your 5,599,881 parameters so hard to understand!??
Просмотров 1604 года назад
A computer-generated tune featured in B. L. Sturm, “What do these 5,599,881 parameters mean? An analysis of a specific LSTM music transcription model, starting with the 70,281 parameters of its softmax layer,” in Proc. Music Metacreation workshop of ICCC, 2018. (themachinefolksession.org/tune/35). Played on The Black Box (highnoongmt.wordpress.com/2020/01/05/introducing-the-black-box).
Introducing: "The Black Box"!
Просмотров 864 года назад
This accordion used to be a club system, but I customized it so that it was capable of reaching Irish traditional ornamentation (i.e., rolls), but still play as a DG accordion. For more information, see: highnoongmt.wordpress.com/2020/01/05/introducing-the-black-box/
Ah Vous dirai-je, intelligence artificielle? (folk-rnn (v2) + Bob L. T. Sturm)
Просмотров 2094 года назад
I created this tune with folk-rnn (v2) to celebrate the 20th anniversary of the International Symposium of Music Information Retrieval. The logo of the conference includes the beginning of Mozart's variation on the French children's song, {\em Ah! Vous dirai-je, maman}. I initialized folk-rnn (v2) with the first two measures, and had it generate the rest. Performed at KTH by Bob L. T. Sturm and...
Birthday Auditory Illusion
Просмотров 774 года назад
Hear the magic created by your brain! (Created for the Music Acoustics course at KTH, 2019)
About folkrnn, the recurrent deep neural network modeling and generation folk-like music
Просмотров 2234 года назад
About folkrnn, the recurrent deep neural network modeling and generation folk-like music
Machine Folk Machine Folk @ ISMIR 2018
Просмотров 2175 лет назад
Machine Folk Machine Folk @ ISMIR 2018
Summer's Almost Done and Gone (folkrnn tune No. 1931)
Просмотров 1245 лет назад
Summer's Almost Done and Gone (folkrnn tune No. 1931)
Softmax Polka (folk-rnn v2) + Tip Top Polka
Просмотров 2296 лет назад
Softmax Polka (folk-rnn v2) Tip Top Polka
what the hell is this? scary music for a normal bycicle horn? -.-
What became of this project? Likewise, it would be fantastic to have access to it.
this is like a fever dream
P𝐫O𝕞O𝓢m
Without a doubt, the most offensive noise I have heard on RUclips.
Be nice to Ruth!
Where are the green-screen effects? Shouldn't you both be floating in outer space? OR in front of a Hawaiian waterfall?
Superbe, bravo ! 😊😊👍👍😊😊
Ah man what an anti-climax :(
It's a pretty tune, but when you play it like an air it is absolutely stunning! I may try to make this a quarantine to learn myself.
'grats Bob!
Played Wonderfully😍
I like it, hihi!
Art the clown!
Hilarious! Great tune
Nice scenery and nice playing ;)
Can you put this on a CD for me but without the cat audio in The Arian
Ha ha. You don't like the no no cat? I can remove from the mix. :)
It's funny, but I guess I just want to hear only what the AI has created. You obviously don't have to though. But it would be very cool if all the separate tracks were on a CD (:
Hey Bob Sturm can you please remove the noise from The Arian
Which software are you using there?
Matlab... python?
MATLAB
...what?
Gee I Wonder Whether This Was Computer Generated
Not this one! This is a real traditional tune. :)
A tried it a tad slower: soundcloud.com/weltsauerstoff/1166-conquest-of-brittany
Wonderful! That was real quick. :) I love the chord progression.
Erie. Still, quite interesting.
A classic of the genre.
Μαλακίες .
I am triggered
Pretty interesting. Did you record that with a speaker-to-microphone setup? Sounds that look like a baby/child voice can be heard at several spots during "Arian, The", especially at the end of it 06:23-06:26 . These are not generated with the musical score, are they?
Thanks. No, it is all from synthetic instruments I mixed in Reaper. The sound you hear is from a particularly famous viral video. Artistic license. :) I didn't have to pitch shift it either.
Why did you put it there
Hahahaha
"the humours of time pigeon." is my favorite title ever. and did i hear the "oh my long John" cat in "the arian?" omg! awesome!
Thanks for listening! Yes, the "no no no cat" is in there. I didn't even have to pitch shift it either.
I laughed so hard
Do you also have more recent experiments? You keep uploading stuff that apparently already is two years old. Which, mind you, isn't bad for the music. It's just that, within two years, a lot could happen in AI. A folk-rnn 2.0 from today might be much better than the one you used back then.
Hi Kram. While this piece was produced by the original folk-rnn, we have constructed several other versions since then and have been studying their properties. Have you heard this? highnoongmt.wordpress.com/2016/12/24/taking-a-christmas-carol-toward-the-dodecaphonic-by-derp-learning/ We also have several new pieces coming up at this workshop: highnoongmt.wordpress.com/2017/02/28/mar-25-folk-music-composed-by-a-computer-inside-out-festival/ Then there is our concert coming up, which will feature new stuff too: highnoongmt.wordpress.com/2017/02/26/partnerships-tickets-tue-23-may-2017-at-1900-eventbrite/
Unfortunately it won't be easy for me to get to Great Britain but I'm glad to hear/read that you are also working on new stuff :) I like both of those compositions drawn from Christmas music although I gotta say neither seem particularly Christmassy. - Which isn't necessarily a bad thing. They actually sound a good deal more interesting than most Christmas music.
So by "best" you mean "best-matching", right? In that case it'd be hardly surprising for the algorithm to get it right. I think you need to add some conditionals on that to make these more music-like. But wait, this was almost two years ago. How have things changed? Surely there is a better state of the art out there now? And a bunch of new and impressive work on musical generation has since been done.
Thanks Kram. In this case, "best" means the posterior probability of the classification is at least 0.9999. The point of this experiment was to show how misleading "classification accuracy" is for music genre recognition. Since that time, things haven't changed. Most researchers are still using classification experiments to measure success in "genre recognition".
I see. I think I agree that perhaps researchers put a bit too much merit in such ideas. Though with better architectures, the model could probably be improved. Notably on the image generation side of things, huge improvements were made just recently, using things like priors that tell the system how natural images actually look like, or General Advisorial Networks (GANs) which learn to tell it whether what it produces is actually what it thinks it produces. I'd imagine such would greatly improve the genre classifier too, especially with respect to robustness against otherwise very easily generated match outliers. (By which I don't mean that they are rare but rather that they are far away from the actual examples they are trained on. - if the system you picked actually is trained like a NN anyway... Though I'd imagine such a task to be precisely where NNs shine, compared to hand-corded techniques)
It sounds like so many other songs. Neat!
Very unconventional but nice. It still is somewhat repetitive at times but it's much closer to something actually cohesive than most computer-synthesized music. Your orchestration certainly helps that of course, but still
مرحبا
مرحبا
Hello!
Insanity. Easily the best RNN music I've heard so far. Not even close. Thanks!: )
+Károly Zsolnai-Fehér (Two Minute Papers) Thanks! Keep in mind that a significant amount of magic comes from the orchestration, which is entirely due to me. Also, I selected these pieces from over 100,000 ABC outputs of the system because I like how much they "fail" to represent the training material. :)
Hey love both of your work Bob Sturm and Two Minute Papers. I have checked out most of your videos Károly they're all fantastic. Bob I have a question: I have recently graduated and have been self-teaching some ML for the past month I have a few of the necessary basics down and am now looking into neural networks. More specifically I am going over the CS224 course on RNNs. Would you recommend any books/literature on neural networks which tackle the intersection of neural networks and music generation? Many thanks to both of you for your hard work
Starts off sort of normally then goes full Zappa.
quite dramatic
Lovely.
1:23 : ?????????
Didn't you even notice all the things blowing up behind you? Impervious?
Is this software available for download anywhere online? I've looked quite a bit and only find the paper. I ask because I'm a master's student, studying music composition and am giving a presentation on Atomic Decomposition for my Electro-Acoustic Music class on Monday. I thought it would be better to actually have the software so I could perform decompositions during the presentation than to simply play this video. Thanks for any help you can give.
Beautifully played,I think you both have enormous talent ,and in time you will both be A1 on your chosen instruments . Good that you enjoy the spirit of olde English morris music from long ago!!!
Yes! Nice recording! And it is a good way to learn the difference between draw-push-draw and push-draw-push !
very nice!
Bob Strum this a wonderful....it is also to MIDI With the well timed MIDI arrangement you have gone a long way You are half way there All the best
Thank you NJKatwoman! You can add your own Ploink if you want. :)
Just curious as to what all of that "clacking" noise is? I thought that was sweet when your Father in law and your wife toasted each other. :D
So I finally got my button accordion about a month ago, and am enjoying learning how to play it. And I am in the process of learning this tune, but I keep stopping and waiting for the "PLOINK"! lol!