AES E-Library

Music Archive Metadata Processing Based on Flow Graphs

The paper addresses the capabilities that should be expected from intelligent Web search tools in order to respond properly to user's music information retrieval needs. An advanced query algorithm was engineered employing a concept of inference rule derivation from flow graphs with regard to semantic data processing. This concept, introduced recently by Pawlak, is used for mining knowledge in databases. The created database searching engine utilizes knowledge acquired in advance and stored in flow graphs in order to enable searching in musical repositories. Results obtained show that employing the implemented method the resulting search matches are ranked optimally, thus metadata related to recorded sound can be retrieved efficiently with the use of this algorithm.

Authors: Kostek, Bozena; Czyzewski, Andrzej
Affiliation: Gdansk University of Technology, Multimedia Systems Department, Gdansk, PL
AES Convention:116 (May 2004) Paper Number:6138 Import into BibTeX
Session Subject:Audio Recording and Reproduction; Archiving and Content Management

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 116Papers)   /116/6138.pdf

Start a discussion about this paper!