Sounds Like Bach

UNC<br>Normal<br>UNC<br>2004-12-05T18:59:00Z<br>2004-12-05T19:01:00Z<br>1980<br>11289<br>UNC<br>94<br>26<br>13243<br>10.4219

Clean<br>Clean

MicrosoftInternetExplorer4

Sounds Like Bach

But the day when music is finally and irrevocably reduced to<br>syntactic pattern and pattern alone will be, to my old-fashioned way of<br>looking at things, a very dark day indeed.

DOUGLAS HOFSTADTER

Back when I was young -- when I wrote "G�del, Escher,<br>Bach" -- I asked myself the question "Will a computer program ever<br>write beautiful music?", and then proceeded to speculate as follows:<br>"There will be no new kinds of beauty turned up for a long time by<br>computer music-composing programs... To think -- and I have heard this<br>suggested -- that we might soon be able to command a preprogrammed<br>mass-produced mail-order twenty-dollar desk-model 'music box' to bring forth<br>from its sterile circuitry pieces which Chopin or Bach might have written had<br>they lived longer is a grotesque and shameful misestimation<br>of the depth of the human spirit." I went on and on in this vein.

What do I make of such speculations now, a quarter-century<br>later? I am not quite sure. I have been grappling for several years now with<br>these issues, and still there is no clear resolution.

In the spring of 1995, I came across the book "Computers<br>and Musical Style" by David Cope, a professor of music at the University<br>of California at Santa Cruz, and in its pages I noticed a mazurka supposedly<br>in the style of Chopin, written by Cope's computer<br>program EMI (short for "Experiments in Musical Intelligence"). This<br>intrigued me because, having revered Chopin my<br>entire life, I felt certain that no one could pull the wool over my eyes in<br>this department. So I went straight to my piano and sight-read through the<br>EMI mazurka several times, with mounting confusion and surprise.

Though I felt there were a few little glitches here and there, I<br>was impressed, for the piece seemed to "express" something. Had I<br>been told it had been written by a human, I would have had no doubts about<br>its expressiveness. It sounded slightly nostalgic, had a bit of Polish<br>feeling in it, and it did not seem in any way plagiarized. It was new, it was<br>unmistakably "Chopin-like" in spirit, and it did not feel<br>emotionally empty. I was truly shaken. How could emotional music be coming<br>out of a program that had never heard a note, never lived a moment of life,<br>never had any emotions whatsoever?

The more I grappled with this, the more disturbed I became --<br>but also fascinated. There was a counterintuitive paradox here, something<br>that obviously had caught me enormously off guard, and it was not my style to<br>merely deny it and denounce EMI as "trivial" or<br>"nonmusical". To do so would have been cowardly and dishonest. I<br>was going to face this paradox straight on; I was going to grapple with this<br>strange program that was threatening to upset the apple cart that held many<br>of my oldest and most deeply cherished beliefs about the sacredness of music,<br>about music being the ultimate inner sanctum of the human spirit, the last<br>thing that would tumble in AI's headlong rush towards thought, insight, and<br>creativity.

Had I only read about EMI's architecture and not heard any of<br>its output, I would have paid little or no attention to it. Although Cope has<br>put in far more work on EMI than most AI researchers ever do on any one<br>project, its basic principles simply did not sound radically new to me, or<br>even all that promising. What made all the difference in the world for me was<br>carefully listening to EMI's compositions.

Over the next few months, I lectured about EMI in many places<br>around the United States and Canada, and what I found truly surprising was<br>that hardly anyone in my audiences seemed upset at Cope's<br>coup in the modeling of artistic creativity; hardly anyone seemed threatened<br>or worried at all. I, on the other hand, felt that something of the<br>profundity of the human mind's sublimity was being taken away. It seemed<br>somehow humiliating, even nightmarish, to me.

The deepest underlying principle behind EMI is what Cope terms<br>"recombinant music" -- the identification of recurrent structures<br>of various sorts in a composer's output, and the reusing of those structures<br>in new arrangements, so as to construct a new piece "in the same<br>style". One can thus imagine feeding in Beethoven's nine symphonies, and<br>EMI coming out with Beethoven's Tenth.

EMI's central modus operandi, given a set of input pieces, is:

(1) chop up; (2) reassemble.

There are, of course, significant principles constraining what can be tacked<br>onto what, and these principles are formulated so as to guarantee coherence.<br>I summarize these two principles as follows:

(1) Make the local flow-pattern of each voice similar to that in source<br>pieces;

(2) Make the global positioning of fragments similar to that in source<br>pieces.

These could be likened to two types of constraints that a jigsaw-puzzle<br>solver naturally exploits when putting together a jigsaw puzzle:

(1)...