Machines Like Us – Science News

Computers and music have been linked since the earliest days of the mainframe, when giant machines controlled primitive synthesizers. Recently, however, a significant advancement has taken place in the field of computer music with the development of software that can not only transcribe polyphonic music in real time, but can also play back complex harmonies alongside human performers. For instance, at the annual Music Information Retrieval Exchange (MIREX) competition, Christopher Raphael of Indiana University demonstrated a system that can understand live music well enough to accompany a musician.

"Technology is changing our sense of what music can be," Raphael says. "The effect is profound." The new software was not easy to develop, however. Raphael compares it to the slow progress in effective speech recognition. "There's been a veritable army of people who've worked on speech recognition for several decades, and [the problem] still remains open," he says. "Any time you deal with real data, there is a huge amount of variation that you have to understand."

Read full story in ARS Technica