Pianist style: can it be measured and recognized?

ABSTRACT

Every musician has a unique style of playing music. This research focuses on the stylistic patterns found in solo jazz and blues performances of pianists. This paper identifies dynamic variance as a factor contributing to the unique "style" of a pianist. A program, NamePianist, was implemented to analyze music from MIDI files based on a metric created to capture a pianist's dynamic style. NamePianist was trained on the style of five different pianists and then used to identify the performer of an unknown song. Two strategies of identification were tested. One identified the performer based on the known song that was closest to the new song. The second strategy created a composite for each performer and then used those composites to identify the performer. This paper presents the details of the metric created and the results of the tests conducted.

REFERENCES

• 1: Biles, John A. "GenJam: A Genetic Algorithm for Generating Jazz Solos." Proceeding of the 1994 International Computer Music Conference, ICMA, San Francisco, 1994.
• 2: Cope, David. Virtual Music: Computer Synthesis of Musical Style. The MIT Press. Cambridge, Massachusetts. 2001.
• 3: Crawford, Walt. "MIDI and Wave: Coping with the Language." Online, Jan/Feb96, Vol. 20 Issue 1, p86.
• 4: Enborne Computing Limited. United Kingdom of Great Britain and Northern Ireland. www.enborne.com, 2001.
• 5: Gwee, Nigel. "Capturing Human Musical Preferences With Fuzzy Application of Rules." Proceedings of the 40th Annual ACM Southeast Conference, Raleigh, North Carolina, April 26--27, 2002.
• 6: Hornel, Dominik and Olbrich, Frank. "Comparative Style Analysis with Neural Networks." In the Proceedings of the 1999 International Computer Music Conference, Beijing, 1999.
• 7: MIDI Association. "Standard Midi Files 1.0." The International MIDI Association. 5316 W. 57th St. Los Angeles, CA 90056 USA, July 1988.
• 8: PGMusic Inc. 29 Cadillac Ave. Victoria, B. C. V8Z 1T3. www.pgmusic.com, 2001.
• 9: Ratner, Leonard G. Music: The Listener's Art. McGraw-Hill Book Company. San Francisco, CA. 1966.
• 10: Belinda Thom, BoB: an interactive improvisational music companion, Proceedings of the fourth international conference on Autonomous agents, p.309-316, June 03-07, 2000, Barcelona, Spain [doi>10.1145/336595.337510]
• 11: Thompson Jr., Charles L.; Langan, David D.; and Doran, Michael V. "Computer Metrics to Analyze Musical Style." Proceedings of the 40th Annual ACM Southeast Conference, Raleigh, North Carolina, April 26--27, 2002.
• 12: Westrup, J. A. and Harrison, F. L1. The New College Encyclopedia of Music. W. W. Norton and Company Inc. New York, New York. 1960.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.5 Programming Languages and Software

General Terms:
Algorithms, Experimentation, Human Factors, Languages, Measurement, Theory

Keywords:
AI metrics, MIDI files, music metrics, pianist style, style recognition