andrew@computing-maths.cardiff.ac.uk (Andrew Jones) (11/07/89)
As a complete newcomer to the Neural Net arena, I would be interested to know what research has been done in the area of Neural Networks for musical applications. Any thoughts? Thanks in advance, Andrew Jones University of Wales College of Cardiff Department of Computing Mathematics Mathematics Institute Cardiff CF2 4AG (andrew@computing-maths.cardiff.ac.uk)
eliot@phoenix.Princeton.EDU (Eliot Handelman) (11/12/89)
In article <882@cf-cm.UUCP> andrew@computing-maths.cardiff.ac.uk (Andrew Jones) writes:
;As a complete newcomer to the Neural Net arena, I would be interested to
;know what research has been done in the area of Neural Networks for musical
;applications. Any thoughts?
;
;Thanks in advance,
;
;Andrew Jones
;University of Wales College of Cardiff
;Department of Computing Mathematics
;Mathematics Institute
;Cardiff CF2 4AG
The problems that seem interesting are engineering problems (like the
recognition of instruments or of polyphony), but that hasn't prevented
a certain amount of "work" in "music." I suggest you leave that to the
musicians.
E. Handelman
Music Dept.
Princeton U.rr2p+@andrew.cmu.edu (Richard Dale Romero) (11/13/89)
Well, I don't know of any work, but a friend and I have talked about it.
It's kind of a project we hope to get around to. Basically, we feel
that neural nets can be used in a recursive connectionist system that
could generate original music. We don't have access to the computing
power necessary to test the ideas, yet, but we should within a year or
so. If you are interested in exactly how we are planning on
implementing everything, I can give some references on recursive
networks. The music aspect comes from both of our (somewhat limited)
musical experience. Feel free to send any questions straight to me if
you have any.
Rick
Romero
And on cold leather seats, It suddenly struck me,
I just might die with a smile on my face after all
- The Smiths schiebel@a.cs.wvu.wvnet.edu (Darrell Schiebel) (11/18/89)
In article <11471@phoenix.Princeton.EDU>, eliot@phoenix.Princeton.EDU (Eliot Handelman) writes: > In article <882@cf-cm.UUCP> andrew@computing-maths.cardiff.ac.uk (Andrew Jones) writes: > ;As a complete newcomer to the Neural Net arena, I would be interested to > ;know what research has been done in the area of Neural Networks for musical > ;applications. Any thoughts? > > The problems that seem interesting are engineering problems (like the > recognition of instruments or of polyphony), but that hasn't prevented > a certain amount of "work" in "music." I suggest you leave that to the > musicians. > > E. Handelman > Music Dept. > Princeton U. I'd suggest getting the paper by Teuvo Kohonen entitled "A Self-Learning Musical Grammar, or `Associative Memory of the Second Kind'"; it was published in the International Joint Conference on Neural Networks June 18-22, 1989. The music generated was quite beautiful. BTW: Teuvo Kohonen, Helsinki University of Technology, Laboratory of Computer and Information Science, Rakentajanaukio 2 C, SF-02150 Espoo, Finland. Darrell Schiebel (schiebel@a.cs.wvu.wvnet.edu)
andrew@computing-maths.cardiff.ac.uk (Andrew Jones) (11/28/89)
I would like to thank all those who have e-mailed responses to my original request concerning musical applications of Neural Networks. Each message was very welcome. I have replied to each message I have received, so hopefully the mailers are already aware of my gratitude. Some of the mailers asked if I could summarize responses to the net. A number of people pointed me towards the work of Teuvo Kohonen. He has published the following paper: A Self-Learning Musical Grammar, or 'Associative Memory of the Second Kind' International Joint Conference on Neural Networks, 1989, Vol 1, p. I-1 to I-5. Apparently the music generated has something of the flavour of J.S. Bach. I understand that Teuvo Kohonen will present a "Neural Concert" on Monday Jan. 15th, 1990 at the 1990 IJCNN. I wish I could be there! Apart from this, the Computer Music Journal has devoted Vol. 13 nos. 3 & 4 to this topic. Rick Romero (rr2p+@edu.cmu.andrew) stated that he is considering getting involved in this area; Andrew McCallum (andrewm@edu.dartmouth.eleazer) informed me that Jamshed Bharucha, Prof. of Psychology at Dartmouth College, has been doing research into NN's and the perception of music for quite a while. He can be reached at bharucha@dartmouth.edu. Finally, I have not yet received a posting by Eliot Handelman, except that Darrell Schiebel included at least part of it in his posting (things are V E R Y S L O W getting through to us at the moment). Eliot Handelman is saying, I think, that non-musicians should avoid this subject area. One of the people who e-mailed me stated that he disagreed with this opinion. I suppose it depends what you mean by "musician". Anyway, thanks again to all those who expressed an interest! ANDREW ======
eliot@phoenix.Princeton.EDU (Eliot Handelman) (12/02/89)
In article <1120@cf-cm.UUCP> andrew@computing-maths.cardiff.ac.uk (Andrew Jones) writes:
;Finally, I have not yet received a posting by Eliot Handelman, except
;that Darrell Schiebel included at least part of it in his posting (things
;are V E R Y S L O W getting through to us at the moment). Eliot Handelman
;is saying, I think, that non-musicians should avoid this subject area.
;One of the people who e-mailed me stated that he disagreed with this
;opinion. I suppose it depends what you mean by "musician".
Everyone can do, of course, exactly what they like.
My definition of a musician is "a person who tries to make a living
from his musical activities." This person was probably in training for
10 or 20 years, has to teach piano or theory to get by, etc.
I sometimes read papers written by people in AI that argue for the relevence
of their research because of potential compositional utility. This miffs me.
If the justification of research is that it generates music, then anyone ought
to be equally useful who can do the same, which includes countless numbers of
hard working composers who don't have the same access to National Science
Foundation grants.
On a music-theoretical, music-cognitive, music-perceptual front, there is
a ton of "research" floating around that is bloody amateurish from a musical
point of view, and I'm just wondering how it is that we musicians are being
usurped in our own professional capacities by non-professionals.