The Null Device
Advances in computer music recognition
Science News has an article about recent advances in computer music processing
. There has been success in creating software which understands recorded music, to the point of being able to extract note information from a (polyphonic, multitimbral, acoustically imperfect) recording. This has been achieved not by programming in rules of musical theory but by using machine learning techniques, setting up a learning system and training it from examples to infer its own rules of music:
He started with a program that had no information about how music works. He then fed into his computer 92 recordings of piano music and their scores. Each recording and score had been broken into 100-millisecond bits so that the computer program could associate the sounds with the written notes. Within those selections, the computer would receive an A note, for example, in the varying contexts in which it occurred in the music. The software could then search out the statistical similarities among all the provided examples of A.
In the process, the system indirectly figured out rules of music. For example, it found that an A is often played simultaneously with an E but seldom with an A-sharp, even though the researchers themselves never programmed in that information. Ellis says that his program can take advantage of that subtle pattern and many others, including some that people may not be aware of.
The software thus developed got impressively good results in music transcription tests (68% accuracy, with the runner-up, a traditional rule-based system, getting 47%). There are numerous applications of such a technology, from automated accompanyists to "musical spellcheckers" to ways of "decompiling" recordings to a score:
Score-alignment programs could be used after a musician records a piece of music to do the kind of fine-tuning that's now performed painstakingly by recording studios, fixing such problems as notes that are slightly off pitch or come in late. "It'll be kind of like a spell-check for music," says Roger Dannenberg, a computer scientist at Carnegie Mellon University in Pittsburgh who is developing the technology.
Christopher Raphael begins the third movement of a Mozart oboe quartet. As his oboe sounds its second note, his three fellow musicians come in right on cue. Later, he slows down and embellishes with a trill, and the other players stay right with him. His accompanists don't complain or tire when he practices a passage over and over. And when he's done, he switches them off.
Not everybody's happy with this, though; musicians' unions, which have opposed "virtual orchestras", are about as keen on it as buggy-whip manufacturers were on the automobile.
There are no comments yet on "Advances in computer music recognition"