Collaborative Use of Features in a Distributed System for the Organization of Music Collections - Intelligent Music Information Systems: Tools and Methodologies - page 148

Chapter VII
Collaborative Use of Features in
a Distributed System
for the Organization of
Music Collections

Ingo Mierswa
University of Dortmund, Germany

Katharina Morik
University of Dortmund, Germany

Michael Wurst
University of Dortmund, Germany

aBstract

Today, large audio collections are stored in computers. Their organization can be supported by machine
learning, but this demands a more abstract representation than is the time series of audio values. We have
developed a unifying framework which decomposes the complex extraction methods into their building
blocks. This allows us to move beyond the manual composition of feature extraction methods. Several
of the well-known features, as well as some new ones, have been composed automatically by a genetic
learning algorithm. While this has delivered good classifications it needs long training times. Hence,
we additionally follow a metalearning approach. We have developed a method of feature transfer which
exploits the similarity of learning tasks to retrieve similar feature extractions. This method achieves
almost optimal accuracies while it is very efficient. Nemoz, an intelligent media management system,
incorporates adaptive feature extraction and feature transfer which allows for personalized services in
peer-to-peer settings.

IntroductIon

music libraries offer services to the public. Private
collections often consist of about 10,000 audio
files. Hence, the organization of collections has
become an issue. The large central music stores

Collecting and playing music has become a pri-
mary use of personal computers and large digital