Pattern Recognition Algorithms for Polyphonic Music Transcription

The main area of work in computer music related to information systems is known as music information retrieval (MIR). Databases containing musical information can be classified into two main groups: those containing audio data (digitized music) and those that file symbolic data (digital music scores). The latter are much more abstract that the former ones and contain a lot of information already coded in terms of musical symbols, thus MIR algorithms are easier and more efficient when dealing with symbolic databases. The automatic extraction of the notes in a digital musical signal (automatic music transcription) permits applying symbolic processing algorithms to audio data. In this work we analize the performance of a neural approach and a well known non parametric algorithm, like nearest neighbours, when dealing with this problem using spectral pattern identification.

[1]  Anssi Klapuri,et al.  AUTOMATIC TRANSCRIPTION OF MUSIC , 2003 .

[2]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[3]  W. Hess.  Algorithms and devices for pitch determination of speech signals. , 1982, Phonetica.

[4]  Keith D. Martin,et al.  A Blackboard System for Automatic Transcription of Simple Polyphonic Music , 1996 .

[5]  Matija Marolt.  Transcription of polyphonic piano music with neural networks , 2000, 2000 10th Mediterranean Electrotechnical Conference. Information Technology and Electrotechnology for the Mediterranean Countries. Proceedings. MeleCon 2000 (Cat. No.00CH37099).

[6]  Roland Wilson,et al.  Note recognition in polyphonic music using neural networks , 1993 .