Thesis

Title: An Explorative, Hierarchical User Interface to Structured Music Repositories

Complete Version: PDF, BibTeX

Short Version (10 Pages + References and Figures): PDF

Abstract: Due to efficient compression algorithms like MP3, the number as well as the size of digital music repositories have increased dramatically over the past few years. Hence, effective methods for finding pieces of music in such repositories are becoming more and more important. Unfortunately, when working with traditional user interfaces which solely provide text-based search, the user already has to know certain textual properties of the songs he/she is looking for (e.g. name of the artist or album). In contrast, the user interface which has been developed for this thesis is based on graphical visualizations of musical similarities between the pieces contained in the repository. This enables the user to exploratively browse through the collection, an approach which is especially useful for discovering formerly unknown pieces of music.
In order to provide different views of the music collection, five algorithms which process the audio signals to measure musical similarities were analyzed. For this purpose, an evaluation using the results of a manual classification perfomed by the author was conducted. This manual classification is based on a test repository composed of more than 800 MP3-files. Eventually, one rhythm-based and one timbre-based algorithm were selected.
The developed user interface ViSMuC (Visualization of Structured Music Collections) implements a method called Aligned Self-Organizing Maps in which high-dimensional data is represented by a 2-dimensional map. The pieces of music are visualized according to an adjustable weighting of their rhythmic and timbral properties. Forming clusters of similar pieces, the resulting groups are colored with respect to the number of songs they represent. Different colormaps are available for this purpose. Since illustrating all pieces of a medium or large collection on a single map would yield a tremendously complex and thus unusable visualization, the user interface contains two hierarchical components. Firstly, for each region of the map that represents a large number of songs, a new map is provided. Secondly, the directory structure of the repository usually forms a user-defined hierarchy which is also taken into account. Another important part of the user interface is the visualization of arbitrary meta-information, which can be taken, for example, from ID3-attributes or external databases. The used technique illustrates the distribution of the values assigned to the meta-information attributes over the complete map. Together with visualizations that are based on the features gained from the similarity measures and their projection to the map, the images showing these distributions facilitate the interpretation of the map.