Extraction of Audio Descriptors and Their Evaluation in Music Classifiction Tasks

Music Information Retrieval (MIR) is an interdisciplinary research area that has the goal to improve the way music is accessible through information systems. One important part of MIR ist the research for algorithms to extract meaningful information (called feature data) from music audio signals. Feature data can for example be used for content based genre classification of music pieces. This masters thesis constributes in three ways to the current state of the art. First, an overview of many of the features that are being used in MIR applications is given. Second, a large part of the described features are implemented in a uniform framework, called T-Toolbox, which is programmed in the Matlab environment. Third, preliminary evaluations are done investigating how well these methods are suited for automatically classifying music according to categorzizations such as genre, mood and perveived complexity.