Go Back   Flash Flash Revolution > Gaming > Stepmania

Reply
 
Thread Tools Display Modes
Old 03-22-2017, 10:26 PM   #1
tunsz555
FFR Player
 
tunsz555's Avatar
 
Join Date: Apr 2009
Location: Thailand
Posts: 117
Default Dance Dance Convolution : Input raw audio - output simfiles

A recent paper named Dance Dance Convolution is out. You might be interested on reading the whole thing here if you like neural nets : https://arxiv.org/pdf/1703.06891.pdf.



But for short, neural nets is a thing which can decide based on what it had learned. (We designed the net and let it learn, but we have no idea what happens inside that it is able to deduce correct answer given a new input.)

This NN will automatically detects where to put steps (analyzing "onset" in an audio file) on an unseen audio. (Shazam for example, could detect what song it is because it already learned about the song, that's not unseen)

The learning material is 133 ITG files with full difficulties, 8 different note charters.

Then it will decide which note to put at that point in time. The resulting simfile is in this video.
https://www.youtube.com/watch?v=yUc3O237p9M


Luckily it is not that intelligent to do crossovers or gallops XD
__________________
I'm actually a Sargon/5argon

Last edited by tunsz555; 03-23-2017 at 09:23 PM..
tunsz555 is offline   Reply With Quote
Old 03-22-2017, 10:34 PM   #2
blanky!
Banned
D7 Elite KeysmasherFFR Veteran
 
Join Date: Jan 2015
Posts: 164
Send a message via Skype™ to blanky!
Default Re: Dance Dance Convolution : Input raw audio - output simfiles

This
Might be very sick


In all honesty this is probably something we've all thought about but never really taken into serious consideration because of the sheer complexity in making such a program. But it's here now!
blanky! is offline   Reply With Quote
Old 03-22-2017, 10:40 PM   #3
blanky!
Banned
D7 Elite KeysmasherFFR Veteran
 
Join Date: Jan 2015
Posts: 164
Send a message via Skype™ to blanky!
Default Re: Dance Dance Convolution : Input raw audio - output simfiles

From the website:
"The network that predicts step timings has no concept of rhythm or tempo. It simply answers the following question 100 times a second: should there be a step here? We map these to step charts by creating measures with 192 steps at 125BPM. We will release a script soon allowing you to manually set the tempo/offset of a chart to clean things up a little. For now, turn off colored note skins to avoid confusion."

It looks like the remnants of FFR's antiquated system have washed out on the shores of San Diego.
blanky! is offline   Reply With Quote
Old 03-22-2017, 11:00 PM   #4
Wayward Vagabond
Confirmed Heartbreaker
Retired StaffFFR Simfile AuthorFFR Veteran
 
Wayward Vagabond's Avatar
 
Join Date: Jul 2012
Age: 35
Posts: 5,856
Default Re: Dance Dance Convolution : Input raw audio - output simfiles

this is neat kind of reminds me of dancing monkey
__________________
Wayward Vagabond is offline   Reply With Quote
Old 03-22-2017, 11:08 PM   #5
DaBackpack
~ お ま ん こ ~
 
DaBackpack's Avatar
 
Join Date: Mar 2014
Location: unlikely
Age: 30
Posts: 915
Send a message via Skype™ to DaBackpack
Default Re: Dance Dance Convolution : Input raw audio - output simfiles

my adviser sent this to me for lab research today lmao

~ S C I E N C E ~
__________________


Quote:
Originally Posted by Moogy View Post
no one cares
Quote:
Originally Posted by TWG Dan Hedgehog View Post
there are 743 matches for hedgehog suicide on deviantart
that's kind of a sad statistic
DaBackpack is offline   Reply With Quote
Old 03-23-2017, 02:42 AM   #6
FightABunny
FFR Player
 
Join Date: Mar 2004
Posts: 51
Send a message via AIM to FightABunny
Default Re: Dance Dance Convolution : Input raw audio - output simfiles

Looks like there is a working demo of Dance Dance Convolution out there!!

http://deepx.ucsd.edu/ddc

Last edited by FightABunny; 03-23-2017 at 02:55 AM..
FightABunny is offline   Reply With Quote
Old 03-23-2017, 02:52 AM   #7
lurker
ur worst nitemare
FFR Simfile AuthorFFR Veteran
 
lurker's Avatar
 
Join Date: Jan 2003
Age: 32
Posts: 1,626
Default Re: Dance Dance Convolution : Input raw audio - output simfiles

hello duderino i am taking a class on stuff like this atm and i have a couple friends who are working on something similar
beat detection is pretty decent and the patterns chosen are generally quite playable on pad (though on the song i tested i ended up with one 175 bpm 16th note minijack and a 32nd triplet)
__________________
some feathery f**k

Last edited by lurker; 03-23-2017 at 02:55 AM..
lurker is offline   Reply With Quote
Old 03-23-2017, 05:17 AM   #8
RenegadeLucien
FFR Veteran
Skill Rating Designer
Retired StaffFFR Veteran
 
RenegadeLucien's Avatar
 
Join Date: Jan 2016
Age: 27
Posts: 282
Default Re: Dance Dance Convolution : Input raw audio - output simfiles

I feel like this could be massively improved just by allowing the user to input the song's BPM if it is known, rather than try to shove the song through 125BPM which would inevitably cause nearly every arrow to be a few ms offbeat
__________________


RenegadeLucien is offline   Reply With Quote
Old 03-23-2017, 07:38 AM   #9
MinaciousGrace
FFR Player
D7 Elite Keysmasher
 
MinaciousGrace's Avatar
 
Join Date: Dec 2007
Location: nima
Posts: 4,278
Default

this is actually a fairly neat and well written paper and if i cared more about pad i'd prolly take the time to scrutinize it further

just want to point out that this paper defines an increase in difficulty as a successive increase in notes per second relating to a successive decrease in sound audibility

------

after throwing ghost love score at it a few times i am more impressed by the paper than the results

though i supposed it was designed for stepmanias musics and not, you know, real music

------

ok you know what i bet i could make a reasonably playable dump file by throwing a song at it 10 times and overlapping the results

Last edited by Velocity; 03-23-2017 at 09:04 AM..
MinaciousGrace is offline   Reply With Quote
Old 03-23-2017, 08:08 AM   #10
contrapatior
Banned
 
Join Date: Sep 2016
Posts: 191
Default Re: Dance Dance Convolution : Input raw audio - output simfiles



contrapatior is offline   Reply With Quote
Old 03-23-2017, 01:37 PM   #11
shenjoku
Wubalubadubdub
FFR Veteran
 
shenjoku's Avatar
 
Join Date: May 2005
Age: 36
Posts: 1,697
Default Re: Dance Dance Convolution : Input raw audio - output simfiles

Quote:
Originally Posted by contrapatior View Post
true art
Beautiful :')
__________________
boop
shenjoku is offline   Reply With Quote
Old 03-23-2017, 06:13 PM   #12
lurker
ur worst nitemare
FFR Simfile AuthorFFR Veteran
 
lurker's Avatar
 
Join Date: Jan 2003
Age: 32
Posts: 1,626
Default Re: Dance Dance Convolution : Input raw audio - output simfiles

Quote:
Originally Posted by MinaciousGrace View Post
just want to point out that this paper defines an increase in difficulty as a successive increase in notes per second relating to a successive decrease in sound audibility
the first part (linking difficulty to nps) is a lot more accurate for pad charts anyway but the music connection is ??

Quote:
Originally Posted by MinaciousGrace View Post
though i supposed it was designed for stepmanias musics and not, you know, real music
this is more a side effect of peak detection working far better on sounds with sharp attacks, as i've found that it tends to miss notes in synths quite often
__________________
some feathery f**k

Last edited by lurker; 03-23-2017 at 06:20 PM..
lurker is offline   Reply With Quote
Reply


Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)
 
Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump



All times are GMT -5. The time now is 12:33 AM.


Powered by vBulletin® Version 3.8.1
Copyright ©2000 - 2024, Jelsoft Enterprises Ltd.
Copyright FlashFlashRevolution