Title :
Linear Predictive Models for Musical Instrument Identification
Author :
Chétry, Nicolas ; Sandler, Mark
Author_Institution :
Centre for Digital Music, London Univ.
Abstract :
This paper deals with musical instrument identification. The proposed method consists of building the instrument models using a set of linear predictive coefficients, the line spectrum frequencies. The models consist of characteristic short-term spectral envelopes calculated for each instrument in the database. The identification process involves the calculation of a similarity measure between two codebooks, one taken from the models database, one corresponding to the sample to identify. Next, the use of support vector machines as classifier is investigated. The two systems are then applied to the identification of monophonic phrases extracted from commercial recordings. It is shown that good performance can be achieved for the classification of one unknown excerpt amongst 6 instruments
Keywords :
acoustic signal detection; musical instruments; support vector machines; line spectrum frequencies; linear predictive models; musical instrument identification; short-term spectral envelopes; support vector machines; Databases; Frequency; Instruments; Music; Predictive models; Production; Signal processing; Support vector machine classification; Support vector machines; Timbre;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
Print_ISBN :
1-4244-0469-X
DOI :
10.1109/ICASSP.2006.1661253