Professional Documents
Culture Documents
Department of Music
Towson University
8000 York Road
Towson, Maryland 21252 USA
ariza@flexatone.net
c
48
Ariza
49
50
Ariza
51
Related tests of machine aptitude have been proposed. Some of these tests attempt to measure
52
Alternative Tests
Ariza
53
in Godel,
Escher, Bach (Hofstadter 1979). Hofstadter
calls this a little Turing test: readers are asked
to distinguish selections of human-written natural
language and computer-generated text, presented in
an intermingled list (Hofstadter 1979, p. 622). Hofstadter fails to articulate the significant deviations
from Turings model.
Similarly, Kostas Terzidis suggests that if an
algorithmically generated paper created by the Dada
Engine system (Bulhak 1996) was submitted to
a conference and accepted, it may have passed
Turings classic test of computer intelligence
(Terzidis 2006, p. 22). As should be clear, simply
mistaking computer output for human output is not
passing a TT. Appropriately, the author of the Dada
Engine credits Hofstadters little Turing test as a
source of inspiration (Bulhak 1996).
Another alteration of Turings model is demonstrated by the Completely Automated Public
Turing test to tell Computers and Humans Apart,
or CAPTCHA. A CAPTCHA is a now-familiar test
given by a computer to distinguish if a user is
either a human or a machine. While superficially
related to the TT in that the CAPTCHA attempts
to distinguish humans and machines, it is not a
TT: there is no interaction, the medium is often
visual (based on the ability to distinguish distorted
54
Comparison
Musical Directive Toy Test (MDtT)
The interrogator, using a computer interface, sends
a musical directive to two composer-agents. One of
the composers is a machine, the other, a human.
The musical directive could be style- or genredependent, or it could be abstractsomething like
write sad music, write a march, or compose
a musical game. The musical directive might
also include music, such as melodic or rhythmic
fragments upon which the composer-agent would
build. The two composers both receive the directive
and create music. After an appropriate amount
of time (a human scale would be necessary), the
completed music is returned to the interrogator in
a format such as a score, synthetic digital audio, or
digital audio of a recorded performance. A flexible
Ariza
55
56
Ariza
57
58
Discrimination Tests
Ariza
59
60
Ariza
61
62
Ariza
63
64
(Cross 1993, p. 167). Perhaps something like a musical Eliza Effect enables humans to treat aesthetic
artifacts from machines as intentional objects; perhaps, in contrast to the CRA, musical syntax alone
can in some cases suffice for musical semantics.
Ariza
65
Conclusion
As Dennett states of restricted text-based TTs, we
should resist all limitations and waterings-down of
the Turing test . . . they make the game too easy . . .
they lead us into the risk of overestimating the
actual comprehension of the system being tested
(Dennett 1998, p. 11). The MDtT and MOtT are
too easy. Music, as a medium remote from natural
language, is a poor vessel for Turings Imitation
Game. Generative music systems gain nothing
from associating their output with the TT; worse,
overestimation may devalue the real creativity in
the design and interface of these systems.
Iannis Xenakis, considering the history of
computer-aided algorithmic composition systems,
asked: What is the musical quality of these attempts? He answers bluntly: The results from
the point of view of aesthetics are meager . . . hope
of an extraordinary aesthetic success based on
extraordinary technology is a cruel deceit (Xenakis
1985, p. 175). Xenakis here distinguishes the system
66
Acknowledgments
I am grateful for the commentary this article has
received over the many stages of its development.
Thanks to Elizabeth Hoffman and Paul Berg for
discussing some of the initial ideas presented here.
Thanks to Nick Collins for research assistance and
comments on important themes. Thanks to the
anonymous reviewers and the editors for valuable
suggestions.
References
Anonymous. 1998. A Mega Success, Thanks to You.
Telegraph 26 March.
Anonymous. 2000. Are You Smarter Than a Robot.
Telegraph 9 March.
Ariza, C. 2005. Navigating the Landscape of ComputerAided Algorithmic Composition Systems: A Definition,
Seven Descriptors, and a Lexicon of Systems and Research. Proceedings of the International Computer
Music Conference. San Francisco, California: International Computer Music Association, pp. 765
772.
Aucouturier, J., and F. Pachet. 2003. Representing
Musical Genre: A State of the Art. Journal of New
Music Research 32(1):8393.
Bedworth, J., and J. Norwood. 1999. The Turing Test is
Dead. Proceedings of the 3rd Conference on Creativity
& Cognition. New York: Association for Computing
Machinery, pp. 193194.
Belgum, E., et al. 1988. A Turing Test for Musical
Intelligence? Computer Music Journal 12(4):79.
Block, N. 1981. Psychologism and Behaviorism.
Philosphical Review 90(1):543.
Bloomfield, B. P., and T. Vurdubakis. 2003. Imitation
Games: Turing, Menard, Van Meegeren. Ethics and
Information Technology 5(1):2738.
Boden, M. 1990. The Creative Mind: Myths and Mechanisms. New York: Routledge.
Boden, M. A. 1996. Artificial Genius. Discover 17:104
107.
Bringsjord, S., P. Bello, and D. Ferrucci. 2001. Creativity,
the Turing Test, and the (Better) Lovelace Test. Minds
and Machines 11:327.
Bringsjord, S., and D. Ferrucci. 2000. Artificial Intelligence
and Literary Creativity: Inside the Mind of BRUTUS, a
Storytelling Machine. Mahwah, New Jersey: Lawrence
Erlbaum.
Bulhak, A. C. 1996. The Dada Engine. Available online
at dev.null.org/dadaengine/manual-1.0/dada toc.html.
Carroll, N. 1999. Philosophy of Art: A Contemporary
Introduction. New York: Routledge.
Cavell, S. 2002. Must We Mean What We Say?: A Book of
Essays. Cambridge, UK: Cambridge University Press.
Cohen, H. 2002. A Self-Defining Game for One Player:
On the Nature of Creativity and the Possibility of
Creative Computer Programs. Leonardo 35(1):5964.
Collins, N. 2006. Towards Autonomous Agents for
Live Computer Music: Realtime Machine Listening
and Interactive Music Systems. PhD dissertation,
University of Cambridge.
Ariza
67
Holland, S. 2000. Artificial Intelligence in Music Education: A Critical Review. In E. R. Miranda, ed. Readings
in Music and Artificial Intelligence. Amsterdam:
Harwood Academic Publishers, pp. 239274.
Hsu, F. 2002. Behind Deep Blue: Building the Computer
that Defeated the World Chess Champion. Princeton,
NJ: Princeton University Press.
Jefferson, G. 1949. The Mind of Mechanical Man.
British Medical Journal 1:11051110.
Kant, I. 1790. Kritik der Urteilskraft [Critique of Judgment.
Berlin: Lagarde and Friederich.
Kugel, P. 2002. Computers Cant Be Intelligent (. . . and
Turing Said So). Minds and Machines 12(4):563
579.
Kurzweil, R. 1990. The Age of Intelligent Machines.
Cambridge, Massachusetts: MIT Press.
Kurzweil, R. 1999. The Age of Spiritual Machines. New
York: Penguin Books.
Kurzweil, R. 2002. A Wager on the Turing Test: Why
I Think I Will Win. Available online at www.
kurzweilai.net/articles/art0374.html?printable=1.
Kurzweil, R. 2005. The Singularity is Near. New York:
Penguin Books.
Lamb, G. M. 2006. Robo-Music Gives Musicians the
Jitters. The Christian Science Monitor, December 14.
Loebner, H. 1994. In Response. Communications of the
ACM 37(6):7982.
Long Bets Foundation. 2002. By 2029 No Computeror
Machine IntelligenceWill Have Passed the Turing
Test. Available online at www.longbets.org/1.
Lovelace, A. 1842. Translators Notes to an Article on
Babbages Analytical Engine. In R. Taylor, ed. Scientific
Memoirs: Selected from the Transactions of Foreign
Academies of Science and Learned Societies, and from
Foreign Journals. London: printed by Richard and John
E. Taylor, 3:691731.
Loy, D. G. 1991. Connectionism and Musiconomy.
Proceedings of the International Computer Music Conference. San Francisco, California: International Computer Music Association, pp. 364
374.
Marsden, A. 2000. Music, Intelligence and Artificiality.
In E. R. Miranda, ed. Readings in Music and Artificial Intelligence. Amsterdam: Harwood Academic
Publishers, pp. 1528.
Midgette, A. 2005. Play It Again, Vladimir (via Computer). New York Times, 5 June.
Moor, J. H. 1976. An Analysis of the Turing Test.
Philosophical Studies 30:249257.
Moor, J. H. 2001. The Status and Future of the Turing
Test. Minds and Machines 11:7793.
68
Ariza
69
70