AES E-Library

Feature Extraction Methods for the Intelligent Processing of Musical Signals

The purpose of this study was to find appropriate sound parameters to be used for feeding inputs of decision algorithms, such as a neural network or rough-based ones. The quality of the chosen parameters was tested statistically and with the use of a neural network algorithm. Experimental results and conclusions are shown in this paper. Conclusions on the artificial intelligence approach to the automatic recognition of musical timbre are included.

Author: Kostek, Bozena
Affiliation: Technical University of Gdansk, Gdansk, Poland
AES Convention:99 (October 1995) Paper Number:4076 Import into BibTeX
Subject:Signal Analysis and Noise Reduction

Click to purchase paper or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $20 for non-members, $5 for AES members and is free for E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD aes13)   /pp9496/pp9510/4010.pdf

Start a discussion about this paper!