Musical instrument classification using neural networks

Authors:
Mustafa Sarimollaoglu;Coskun Bayrak
Affiliations:
Dept. of Applied Science, University of Arkansas at Little Rock, Little Rock, Arkansas;Dept. of Computer Science, University of Arkansas at Little Rock, Little Rock, Arkansas
Venue:
SIP'06 Proceedings of the 5th WSEAS international conference on Signal processing
Year:
2006

Citing 1
Cited 0

Musical instrument recognition using cepstral coefficients and temporal features

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 02

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a system for automatic classification of musical instrument sounds is introduced. As features mel-frequency cepstral coefficients and as classifiers probabilistic neural networks are used. The experimental dataset included 4548 solo tones from 19 instruments of MIS database (The University of Iowa Musical Instrument Samples). Experiments for different system structures (hierarchical and direct classification) were carried out and compared. The best performance in direct classification was 92% for individual instruments and 97% for families; and 89% for individual instruments when hierarchical approach is used.