This article about David Cope starts off talking about generative music but takes an interesting turn about halfway through when it introduces the interface to Emily Howell, a virtual composer. From the description, the interface basically enables a composer to collaborate with the software composer by letting them engage in a dialogue about the piece of music that they want to create.
“This program would write music in an odd sort of way. Instead of spitting out a full score, it converses with Cope through the keyboard and mouse. He asks it a musical question, feeding in some compositions or a musical phrase. The program responds with its own musical statement. He says “yes” or “no,” and he’ll send it more information and then look at the output. The program builds what’s called an association network — certain musical statements and relationships between notes are weighted as “good,” others as “bad.” Eventually, the exchange produces a score, either in sections or as one long piece.”I wonder how such a dialogue protocol could be tailored to support this kind of interaction. Could we develop protocols that support collaboration and yield well formed pieces of music? What would happen if we had two or more of these virtual composers conversing to produce music?