Re: recognizing a source by its harmonic structure

[Ladislava Janku <jankul@xxxxxxxxxxxxxxxx>]

Hi!
There is lot of work done in music instruments classification by frequency
spectrum, cepstrum or other approaches

For example, the following papers concern this problem:

Brown, J.C. (1999). ``Computer identification of musical instruments using
pattern recognition with cepstral coefficients as features'' J. Acoust. Soc.
Am. 105, 1933-1941.

Herrera P., Amatriain X., Batlle E., and Serra X. Towards Instrument
Segmentation for Music Content Description: a Critical Review of Instrument
Classification Techniques. In Proc. of International Symposium on Music
Information Retrieval, 2000.

Liu, Wan Feature selection for automatic classification of musical
instrument sounds Proceedings of the first ACM/IEEE-CS joint conference on
Digital libraries Roanoke, Virginia, United States Pages: Pages: 247 - 248
Year of Publication: 2001
ISBN:1-58113-345-6

Brown, J.C. (1996). "Frequency ratios of spectral components of musical
sounds" J. Acoust. Soc. Am. 99, 1210-1218.

Brown, J.C., Houix, O. & McAdams, S. (2001) Feature dependence in the
automatic identification of musical woodwind instruments. J. Acoust. Soc.
Am. 109, pp. 1064-1072.

Kinoshita, T., Sakai, S. & Tanaka, H. (1999) Musical soundsource
identification based on frequency component adaptation. Proc. IJCAI-99
Workshop on ComputationalAuditory Scene Analysis, Stockholm, Sweden.

Marques, J. & Moreno, P. (1999) A study of musical instrument classification
using Gaussian mixture models andsupport vector machines. Cambridge Research
LaboratoryTechnical Report Series CRL/4.

Martin, K. (1999) Sound-source recognition: A theory andcomputational model.
PhD Thesis, MIT

G.J. Brown, J. Egging A MISSING FEATURE APPROACH TO INSTRUMENT
IDENTIFICATION IN POLYPHONIC MUSIC, ICASSP03



Ladislava Janku



----- Original Message -----
From: "Gregoire, Jerry" <jgregoire@ECE.MONTANA.EDU>
To: <AUDITORY@LISTS.MCGILL.CA>
Sent: Thursday, June 26, 2003 10:33 PM
Subject: recognizing a source by its harmonic structure


> Does anyone know of work done that categorizes sources by patterns in
their
> harmonic structure.
>
> An example would be to separate a guitar from a flute using the harmonic
> relationships of f0, f1, f2, ... of a guitar compared to the flute's
> harmonics.
>
> Jerry Gregoire
>