Popular version of paper 2aMU5
Presented Tuesday morning, June 4, 2002
143rd ASA Meeting, Pittsburgh, PA

I will discuss my ongoing work, "Music Plus One" --- a computer system that plays the role of a sensitive musical accompanist in a non-improvisatory composition for soloist and accompaniment.

The goals of my "Music Plus One" project are similar to the more familiar "Music Minus One" (MMO). MMO makes a recording of a piece of music for soloist and accompaniment, like a sonata or concerto, but only the accompaniment is actually recorded. The music is preceded by several warning clicks (something like Lawrence Welk's "and a one and a two and a ..."), and the soloist tries to play along with the recording. A heartfelt yet futile battle of wills follows which eventually results in the the live player's unconditional surrender to the robotic insistence of the recording. Thus, contrary to both musical etiquette and common sense, the soloist must follow the accompaniment.

Although MMO has its heart in the right place, in practice it is the antithesis of what the musical experience should be. My project, "Music Plus One" (MPO), tries to deliver the goods that MMO only promises. Specifically, my goals are that the program must respond in real time to the soloist's tempo changes and expressive gestures; the program must learn from past performances so that it assimilates the soloist's interpretation in future renditions; and it must bring a sense of musicality to the performance in addition to what is learned from the soloist. In this way MPO adds to the soloist's experience by providing a responsive and nuanced accompaniment rather than subtracting from it by imposing a rigid framework that stifles musical expression.

My efforts in MPO have been received with suspicion by some. "Why dehumanize music with your cold and unfeeling computers?" I assure the wary reader that my goal is not to take music out of the hands of people. To the contrary, my desire is just the opposite --- to create a proficient, willing, and tireless accompanist for any musician who doesn't happen to have a human accompanist available at the moment. Such a system can be invaluable in learning new repretoire, preparing for performance, and making practice more enjoyable. In this way I hope to get more people involved with music. Additionally, I hope to expand the horizons of interactive musical systems, thereby making new compositions possible not realizable through traditional means. I will perform such a piece, explicitly composed for my system, at the 2002 International Computer Music Conference in Gottenberg, Sweden. My belief is that interactive accompaniment systems will be as important to musicians of the future as the metronome and tuner are today. Perhaps more so.

My talk will focus on the fundamental issue of "hearing" the soliost. More precisely, I discuss the problem of tracking the soloist's progress through a musical score, possibly performed with many errors. As with the human accompanist, the computer hears both the sound generated by both soloist and the accompaniment and must be able to separate between these sources. I will discuss an approach to the problem, analogous to techniques familiar in speech recogntion, that can automatically learn from real data and improve its performance on future data. I will provide a live demonstration of my system on Robert Schumann's 1st Romance for Oboe and Piano.

Example of 1st Romance of Oboe and Piano
More examples and description