The aim of this research was to prepare a database for studying musical instrument timbres. Parameters of both frequency and time domains of musical sounds have been extracted. In order to discretize parameter values, a method of attribute quantization is proposed based on the statistical approach. Experiments concerning musical instrument recognition using rough set and neural network approaches were performed. Conclusions concerning applications of artificial intelligence methods to musical instrument recognition were derived.
(See document for exact affiliation information.)
Click to purchase paper as a non-member 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 Join the AES. If you need to check your member status, login to the Member Portal.
