ka2cs220@uhura.cc.rochester.edu (Steve Berkley) (06/04/91)
If anyone has any suggestions concerning applications of learning systems in a specialized domain of "automatic composition" of music, I would appreciate it. I am researching the feasability of a real-time (NN?) automatic composition program in C, fed with MIDI data. e-mail replies to ka2cs220@uhura.cc.rochester.edu or post -Steve Berkley
cain@ics.uci.edu (Timothy Cain) (06/04/91)
In <14344@ur-cc.UUCP> ka2cs220@uhura.cc.rochester.edu (Steve Berkley) writes: >If anyone has any suggestions concerning applications of >learning systems in a specialized domain of "automatic >composition" of music, I would appreciate it. I am researching >the feasability of a real-time (NN?) automatic composition program >in C, fed with MIDI data. At AAAI-88 in Minneapolis-St.Paul, there was a workshop on this topic. You might want to track down its proceedings (the workshop's, not AAAI's). I don't have it, since I was next door in the planning workshop. Unlike those systems, please include a volume control parameter on your program. :-) Tim. -- Timothy D. Cain Department of Information and Computer Science UC Irvine cain@ics.uci.edu (ARPA)
eiverson@nmsu.edu (Eric Iverson) (06/04/91)
In article <284AB4A5.28201@ics.uci.edu> cain@ics.uci.edu (Timothy Cain) writes: > At AAAI-88 in Minneapolis-St.Paul, there was a workshop on this topic. > You might want to track down its proceedings (the workshop's, not > AAAI's). I don't have it, since I was next door in the planning > workshop. Unlike those systems, please include a volume control > parameter on your program. :-) I have a copy of those proceedings, but would be interested in a copy of the proceedings for the workshop at AAAI-89 in Detroit. Anyone interested in a trade? Also, what happened at the workshop at ECAI '90? I don't recall seeing anything about it here. -- ------------------------------------------------------------------------ Eric Iverson Internet: eiverson@nmsu.edu Computing Research Lab Box 30001/3CRL Life is something to do when New Mexico State University you can't get to sleep. Las Cruces, NM 88003-0001 -Fran Lebowitz VOICE: (505) 646-5711 FAX: (505) 646-6218
punch@pleiades.cps.msu.edu (Bill Punch) (06/05/91)
I have a copy of both the AAAI 88 and the IJCAI 89 conferences, both
containing interesting material. But if you REALLY want to get a lot of
stuff, take a look at the ICMC (International Computer Music Conference)
from almost any year. AI applications (including neural nets) are
interspersed througout. Some are rather outrageous but many are very
interesting. The 91 conference will be held in Montreal on Oct 16-21 at
McGill University, by the way.
>>>bill punch<<<
AI/KBS Lab, Mich State.
punch@pleiades.cps.msu.edueliot@phoenix.Princeton.EDU (Eliot Handelman) (06/09/91)
In article <EIVERSON.91Jun3213332@aigyptos.nmsu.edu> eiverson@nmsu.edu (Eric Iverson) writes: ;In article <284AB4A5.28201@ics.uci.edu> cain@ics.uci.edu (Timothy Cain) writes: ; ;> At AAAI-88 in Minneapolis-St.Paul, there was a workshop on this topic. ;> You might want to track down its proceedings (the workshop's, not ;> AAAI's). I don't have it, since I was next door in the planning ;> workshop. Unlike those systems, please include a volume control ;> parameter on your program. :-) ; ;I have a copy of those proceedings, but would be interested in a copy ;of the proceedings for the workshop at AAAI-89 in Detroit. Anyone ;interested in a trade? I have those proceedings, and there wasn't one article worth reading.
cmunday@gara.une.oz.au (Craig Munday) (06/13/91)
ka2cs220@uhura.cc.rochester.edu (Steve Berkley) writes: >If anyone has any suggestions concerning applications of >learning systems in a specialized domain of "automatic >composition" of music, I would appreciate it. I am researching >the feasability of a real-time (NN?) automatic composition program >in C, fed with MIDI data. Can any one fill me in on the definition of a real-time composition program? Is the term suggesting that a computer is being used to actually compose and play music. I myself can not accept the fact that computers can compose music. Music is suppose to be an expression of ones inner feelings, and because it comes from within it has a great power to move people into different spheres. The feeling that is present in music of the past has induced greated pride in ones country, I doubt that a machine can come close to providing this attribute of music. Convince me that a computer can provide the necessary feeling that music needs. Somethings may better be left alone.
reccmo@uts.uni-c.dk (Christian Mondrup) (06/14/91)
In <6983@gara.une.oz.au> cmunday@gara.une.oz.au (Craig Munday) writes: >ka2cs220@uhura.cc.rochester.edu (Steve Berkley) writes: >>If anyone has any suggestions concerning applications of >>learning systems in a specialized domain of "automatic >>composition" of music, I would appreciate it. I am researching >>the feasability of a real-time (NN?) automatic composition program >>in C, fed with MIDI data. > Can any one fill me in on the definition of a real-time composition >program? Is the term suggesting that a computer is being used to actually >compose and play music. I myself can not accept the fact that computers can >compose music. Music is suppose to be an expression of ones inner feelings, >and because it comes from within it has a great power to move people into >different spheres. The feeling that is present in music of the past has >induced greated pride in ones country, I doubt that a machine can come close >to providing this attribute of music. > Convince me that a computer can provide the necessary feeling that music >needs. Somethings may better be left alone. I have just been reading Douglas Hofstaedter's book 'Goedel, Escher, Bach', where he insists that it is possible and desirable too to model a human mind complete with feelings etc. into a machine. As Hofstaedter is much interested in music he specifically deals with the problem of a 'machine composer' and says that you may very well imagine such a thing. I am not convinced that your statement 'music is suppose to be an expression of ones inner feelings' is always true. Sometimes I think it's just playing with aesthetic matherials, for which purpose you may very well use a computer as a helping tool for composing (Xenakis etc.) - both beautiful and great music may come out of that. But whether music is expressing feelings or just playing I too can't see the point in developing ai for automatic composing.
hotline_muh@rtots1.enet.dec.com (Sammy Fischer) (06/14/91)
In article <6983@gara.une.oz.au>, cmunday@gara.une.oz.au (Craig Munday) writes... [Quotes and some lines deleted] >compose and play music. I myself can not accept the fact that computers can >compose music. Music is suppose to be an expression of ones inner feelings, >and because it comes from within it has a great power to move people into >different spheres. The feeling that is present in music of the past has >induced greated pride in ones country, I doubt that a machine can come close >to providing this attribute of music. I don't think that the feelings you get from listening to a piece of music are always the feelings the composer had when he wrote it down. (especially when listening to mainstream pop (which I do not;')) ... The composer has an Idea of what he WANTS the audience to feel, and tries to translate it into music notes. So ... Why couldn't computers, provided with the feeling that is to be 'produced' and some typical patterns which occure in this sort (e.g. producing the same 'feelings') of music, compose something enjoyable? > Convince me that a computer can provide the necessary feeling that music >needs. Somethings may better be left alone. just tried to. byebye, sammy ----- ******************************************************************************* * Sammy Fischer, Munich, Germany * * (hotline_muh@rtots1.dec.com) * * 'I thought I was a slice of Lemon jumpin' in a Gin tonic' * * (Ford Perfect) * ******************************************************************************* All Standart Disclaimer applying!
bsmith@turing.seas.ucla.edu (Brian Smith) (06/18/91)
I think the whole point about using a machine for automated composition isn't so much replacing the human composer. As someone commented, the computer has been used by many composers as a tool for structuring the many variables of music. We should look at this aspect of computers as a positive, an assist to the actual human who's writing the piece. From an AI standpoint, again, I don't think we should be looking at CPU's as the next Beethoven. However, the processes of creativity really aren't clearly understood, and perhaps we can learn something by trying to model artistic behavior with a computer. After all, musical composition is really (being a bit oversimplistic here) just a very sophisticated planning system, is it not? There was an argument that music is an expression of feeling (which some may argue with, i.e. Cage); in that case, shouldn't we examine HOW emotions and affect influence a musician's plans to reach the goal of a musical piece? Who knows? It probably can't be realized -- MacBach. Yet, I see any such endeavor as a useful task despite the fact that we generally consider music to be connected to humans.Besides, all art forms must be opened up to new ideas or else they become stagnant; the musical revolutions of the 20th century are evidence to support this. Maybe, the computer is the key to push the bounds and traditions of music into its next phase of growth. Brian K. Smith soon to be: RAND Corporation University of Leeds 1700 Main Street School of Computer Studies, AI Group Santa Monica, CA Leeds, LS2 9JT United Kingdom
eliot@phoenix.Princeton.EDU (Eliot Handelman) (06/20/91)
In article <3084@lee.SEAS.UCLA.EDU> bsmith@turing.seas.ucla.edu (Brian Smith) writes:
; However, the processes of creativity really aren't clearly
;understood, and perhaps we can learn something by trying to model artistic
;behavior with a computer. After all, musical composition is really (being a
;bit oversimplistic here) just a very sophisticated planning system, is it not?
The problem is setting constraints for the planner, ie, what constitutes
an admissable "move," so to speak. (Allowing a second simplification of
restricting possible musical actions, but that's like restricting yourself
to a couple of tom-toms -- the nature of problem isn't altered). Musical
constraints are exceptionally difficult to get a hold of, because they are
cognitive, cultural and volatile, rather than formalistic and invariant.
Almost certainly the same is true of creativity.
It's much more interesting to focus on the listener, because apprehension
is the simplest act of creativity. bsmith@turing.seas.ucla.edu (Brian Smith) (06/25/91)
In article <10936@idunno.Princeton.EDU> eliot@phoenix.Princeton.EDU (Eliot Handelman) writes: > >The problem is setting constraints for the planner, ie, what constitutes >an admissable "move," so to speak. (Allowing a second simplification of >restricting possible musical actions, but that's like restricting yourself >to a couple of tom-toms -- the nature of problem isn't altered). Musical >constraints are exceptionally difficult to get a hold of, because they are >cognitive, cultural and volatile, rather than formalistic and invariant. >Almost certainly the same is true of creativity. Yeah, I can buy that. However, I don't think we should be thinking about planning in the GPS sense of initial state leads to goal state thrugh a series of operators. In a sense, we have to redefine the notion of planning for the musical realm. The very fact that MOST composers have to go through extensive periods of refinement as well as complete goal alteration (or, at least, I certainly do) leads me to thing that some sort of "weak" or thematic planner is necessary to perform the task. As well, I see your point about the constraints, and I've certainly argued that autonomous composers lack depth due to the fact that they lack cultural, competence, and performance knowledge. And yet, to oversimply again, couldn't we provide the information to the machine in, say, rules or connectionist paradigms? > >It's much more interesting to focus on the listener, because apprehension >is the simplest act of creativity. Listening is pretty fascinating stuff, but I think that composition is a much more interesting problem since one can't compose without listening. To some extent, everyone is a composer (i.e. humming arbitrary tunes, melodic contours in speech, etc.), so it does seem to be a worthwhile area of study. Once the knwoledge gained through listening is captured, how do we use it in the performance domain? -- brian
ISSSSM@NUSVM.BITNET (Stephen Smoliar) (06/26/91)
In article <3191@lee.SEAS.UCLA.EDU> bsmith@turing.seas.ucla.edu (Brian Smith) writes: >In article <10936@idunno.Princeton.EDU> eliot@phoenix.Princeton.EDU (Eliot >Handelman) writes: >> >>It's much more interesting to focus on the listener, because apprehension >>is the simplest act of creativity. > >Listening is pretty fascinating stuff, but I think that composition is a much >more interesting problem since one can't compose without listening. Where have you been for the last forty years, Brian? Following the Second World War, there was no end of experimentation in music; and much of which emerged had nothing to do with listening (at least at the time of composition). The early days of computer-synthesized sounds provide a good case in point. Composers often labored long and hard to debug the theoretical formulation of what they wanted yet rarely had much intuition regarding what the tape would sound like when all the processing was done. You may wish to take the ethical position that one OUGHT NOT to compose without listening, but do not expect all practicing composers to accept that position. > To some >extent, everyone is a composer (i.e. humming arbitrary tunes, melodic contours >in speech, etc.), so it does seem to be a worthwhile area of study. I think you are homing in on an important point here, Brian; and I would like to try to push it a bit further. What you are really talking about here is BEHAVIOR, and one of my favorite hobby-horses is that there is more to behavior than can be captured in logical calculi or neural nets. The trouble is that we to not do a terribly good job when it comes to DESCRIBING such behavior. The sorts of protocol analyses which were performed by Newell and Simon were little more than self-fulfilling prophecies--descriptions based on a foundation of symbol manipulation which they assumed HAD to be there. Music, on the other hand, does not lend itself to such symbol-based descriptions because, as Ed Hall has been suggesting on comp.music, the actual PRACTICE of MAKING MUSIC has precious little to do with the symbols of music notation. Getting a MACHINE to "make music" (i.e. to exhibit such behavior) may thus be viewed as a major challenge to artificial intelligence, because it is an aspect of behavior which has been ignored (and certainly not accounted for) by most of the progress in AI to date. > Once the >knwoledge gained through listening is captured, how do we use it in the >performance domain? > This is another example of how thinking about music should force us to expand the current horizons of artificial intelligence. Much of the artificial intelligence community seems inclined to live in a world in which "learning" is a matter of adding declarative sentences to some kind of "knowledge base." However, the above sentence captures an element of learning which is much truer to behavior as we know it: How one behaves "in the performance domain" is a reflection of what has happened during past listening experiences. This is not a new idea Brian. Quite some time ago, Minsky wrote a wonderful essay on the role of a musical composition AS TEACHER. Unfortunately, we have made precious little progress in implementing any of these ideas. Nevertheless, those ideas still deserve more attention. After reading Volume 47 of ARTIFICIAL INTELLIGENCE, we should be at least SKEPTICAL about what logical calculi can ultimately offer us. At the very least, we should be encouraged to work on problems which logic does not "fit" as comfortably as it does is, for example, choosing the parameters for the design of an elevator system. What IS "knowledge gained through listening?" We really do not have the slightest idea? We do not yet even have a handle on how we know that what we are hearing NOW is the same tune we heard five minutes ago! So far I have only been able to pursue such questions as peripheral activities, but my current hunch is that SERIOUS attention to these matters may ultimately lead to a significant shift in our current paradigms for artificial intelligence. =============================================================================== Stephen W. Smoliar Institute of Systems Science National University of Singapore Heng Mui Keng Terrace, Kent Ridge SINGAPORE 0511 BITNET: ISSSSM@NUSVM "He was of Lord Essex's opinion, 'rather to go an hundred miles to speak with one wise man, than five miles to see a fair town.'"--Boswell on Johnson