A novel approach to the computer analysis of musical sound features has been made applying learning algorithms to the assessment of subjective scaling factors. A rough set theory recognized in artificial intelligence proven to be especially interesting in applications to acoustical assessments. Foundations of this theory and basic principles underlying the rough set algorithms are shown. Some multidimensional scaling methods of musical timbre are reviewed in order to provide data for the rough set computations. Correspondingly, examples of automatic classifications of sound features are obtained. Conclusions concerning the artificial intelligence approach to the processing of acoustic data are included.
https://www.aes.org/e-lib/browse.cfm?elib=6359
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 and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.
Learn more about the AES E-Library
Start a discussion about this paper!
