Re: [PD] pattern extraction/recognition
Hallo, Dr. Greg Wilder hat gesagt: // Dr. Greg Wilder wrote: Here are a few highly accomplished and respected authors on the subject. Their research is a quick google away... Emilios Cambouropoulos Roger Dannenberg Pierre-Yves Rolland David Temperley Also Robert Rowe's Machine Musicianship is a nice intro to this and related topics. Ciao -- Frank Barknecht _ __footils.org__ ___ PD-list@iem.at mailing list UNSUBSCRIBE and account-management - http://lists.puredata.info/listinfo/pd-list
Re: [PD] pattern extraction/recognition
Hi, i'm looking for a way to make a patch that recognizes musical motifs from a flute player in real-time. The first problem is how accurate you expect the pattern recognition to be. I have a piece where I ask Pd to make binary descriminations on input from the flute player, in real time. It works fine. It is simple enough to get note information from fiddle~ and write that as a list or a table. The problem is that you won't get 100% of the flute notes (legato notes sometime don't trigger etc.) and the notes fiddle estimates are not always perfect. The next problem is how fast can pd process the list/table to identify pattern. That will depend on the length of the patterns (of course) but also the narrower the definition of what pd needs to look for the faster it can match (probably). To create a system that works for you, you will definately need to start with recordings before you have something to work with a player on. There is a fair ammount of research on music pattern recognition out there, though real-time is not a priority for most at this stage. Oded ___ PD-list@iem.at mailing list UNSUBSCRIBE and account-management - http://lists.puredata.info/listinfo/pd-list
Re: [PD] pattern extraction/recognition
the best performance I ever heard using musical pattern recognition was by the trombone player george lewis http://en.wikipedia.org/wiki/George_Lewis_(trombonist) he uses a max patch called voyager. I have no idea how it works, maybe you find some documentation online. he worked on it for several years. and it was extremely good. marius. Oded Ben-Tal wrote: Hi, i'm looking for a way to make a patch that recognizes musical motifs from a flute player in real-time. The first problem is how accurate you expect the pattern recognition to be. I have a piece where I ask Pd to make binary descriminations on input from the flute player, in real time. It works fine. It is simple enough to get note information from fiddle~ and write that as a list or a table. The problem is that you won't get 100% of the flute notes (legato notes sometime don't trigger etc.) and the notes fiddle estimates are not always perfect. The next problem is how fast can pd process the list/table to identify pattern. That will depend on the length of the patterns (of course) but also the narrower the definition of what pd needs to look for the faster it can match (probably). To create a system that works for you, you will definately need to start with recordings before you have something to work with a player on. There is a fair ammount of research on music pattern recognition out there, though real-time is not a priority for most at this stage. Oded ___ PD-list@iem.at mailing list UNSUBSCRIBE and account-management - http://lists.puredata.info/listinfo/pd-list ___ PD-list@iem.at mailing list UNSUBSCRIBE and account-management - http://lists.puredata.info/listinfo/pd-list
Re: [PD] pattern extraction/recognition
thanks all for reply, the best performance I ever heard using musical pattern recognition was by the trombone player george lewis http://en.wikipedia.org/wiki/George_Lewis_(trombonist)http://en.wikipedia.org/wiki/George_Lewis_%28trombonist%29 he uses a max patch called voyager. I have no idea how it works, maybe you find some documentation online. he worked on it for several years. and it was extremely good. marius. thanks a lot, in this paperhttp://muse.jhu.edu/demo/leonardo_music_journal/v010/10.1lewis.html,George talk about the voyager programming in the FORMULA language, some interesting insights, thinking buy the cd http://www.amazon.com/gp/redirect.html%3FASIN=B3JAI9%26tag=squidoox14-20%26lcode=xm2%26cID=2025%26ccmID=165953%26location=/o/ASIN/B3JAI9%253FSubscriptionId=19BAZMZQFZJ6G2QYGCG2 Have begun to look Nick Collins work (bbcut), that looks to be very good with supercollider. Looks that legato notes are a problem with fiddle~. Maybe a output mix of fiddle~ and fft~? just guessing. I think that the length of the pattern to be recognized should be variable, but following the common sense concept of motif: 3 to 10 notes. The motif is a rythmic/melodic pattern - i will think rythm and melody separately, but in some moment they will interact i still don't figure out how. Aubio semms great, i will try a binary that i found herehttp://ftp.man.poznan.pl/pub/linux/debian/debian/pool/main/a/aubio/pd-aubio_0.3.2-2+b1_i386.deb. Looks like i have a lot of work to do. Thanks ___ PD-list@iem.at mailing list UNSUBSCRIBE and account-management - http://lists.puredata.info/listinfo/pd-list
