The first wave of interactive music systems relied almost exclusively on the Musical Instrument Digital Interface (MIDI) standard, a symbolic representation of music modeled closely on the behavior of a piano keyboard, as well as traditional concepts of music notation. The second wave takes as its input raw audio signals, a sub-symbolic data representation that is far more flexible while being far less structured. This article will consider the issues involved with building a pathway back up from sub-symbolic systems to the symbolic approaches of the first wave, and the relative advantages of the two.