Automatic transcription of musical recordings

An automatic music transcription system is described which is applicable to the analysis of real-world musical recordings. Earlier presented algorithms are extended with two new methods. The first method suppresses the non-harmonic signal components caused by drums and percussive instruments by applying principles from RASTA spectrum processing. The second method estimates the number of concurrent voices by calculating certain acoustic features in the course of an iterative multipitch estimation system. Accompanying audio demonstrations are at http://www.cs.tut.fi/~klap/iiro/crac2001.

[1]  David Huron.  Voice Denumerability in Polyphonic Music of Homogeneous Timbres , 1989 .

[2]  Hynek Hermansky,et al.  Recognition of speech in additive and convolutional noise based on RASTA spectral processing , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Anssi Klapuri,et al.  Sound onset detection by applying psychoacoustic knowledge , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[4]  Anssi Klapuri,et al.  Robust Multipitch Estimation for the Analysis and Manipulation of Polyphonic Musical Signals , 2000 .

[5]  Antti Eronen,et al.  Comparison of features for musical instrument recognition , 2001, Proceedings of the 2001 IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics (Cat. No.01TH8575).

[6]  Anssi Klapuri,et al.  Separation of harmonic sounds using multipitch analysis and iterative parameter estimation , 2001, Proceedings of the 2001 IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics (Cat. No.01TH8575).