Adaptive Methods for User-Centered
Organization of Music Collections
Dissertation, Sebastian Stober
Otto-von-Guericke University
Magdeburg, Germany
submitted September 21, 2011
defended November 15, 2011
ISBN 978-3-8439-0229-8
published by Verlag Dr. Hut
digital version (PDF)
slides of the defense (PDF)
Abstract
Music Information Retrieval (MIR) systems have to deal with multi-faceted music information and very heterogeneous users. Especially when the task is to organize a music collection, the diverse perspectives of users caused by their different level of expertise, musical background or taste pose a great challenge. This challenge is addressed in this book by proposing adaptive methods for several elements of MIR systems: Data-adaptive feature extraction techniques are described that aim to increase the quality and robustness of the information extracted from audio recordings. The classical genre classification problem is approached from a novel user-centric perspective – promoting the idea of idiosyncratic genres that better reflect a user’s personal listening habits. An adaptive visualization technique for exploration and organization of music collections is elaborated that especially addresses the common and inevitable problem of projection errors introduced by dimensionality reduction approaches. Furthermore, it is outlined how this technique can be applied to facilitate serendipitous music discoveries in a recommendation scenario and to enable novel gaze-supported interaction techniques. Finally, a general approach for adaptive music similarity is presented which serves as the core of many adaptive MIR applications. Application prototypes demonstrate the usability of the described approaches.
Media Clips
The following media clips serve as additional illustration for the thesis. They need to be in the sub-directory “media/” relative to the PDF for the links to work properly.
- Audio Clip 1: VoiceExtraction-1-Original.wav
Original 22 seconds clip from “Have a little faith in me” by Joe Cocker. - Audio Clip 2: VoiceExtraction-2-Karaoke.wav
Approximated karaoke version of Audio Clip 1. - Audio Clip 3: VoiceExtraction-3a-GlobalNoiseProfile.wav
Filtered melody extracted from audio clip 1 using a global noise profile from Audio Clip 2. - Audio Clip 4: VoiceExtraction-3b-LocalNoiseProfile.wav
Filtered melody extracted from audio clip 1 using a local noise profile from Audio Clip 2.
- Video Clip 1: MusicGalaxyH264.mov
Demonstration video clip for the MusicGalaxy user interface prototype created for the ISMIR’10 late breaking demo. - Video Clip 2: PhotoSelectionTaskH264.mov
Excerpt of a recorded session as part of the evaluation of the focus-adaptive SpringLens visualization technique. The gaze trajectory is visualized by red lines and filled red circles (size increases with time). Mouse clicks are highlighted by red (left button) and green (right button) circles. - Video Clip 3: BeatlesExplorerH264.mov
Demonstration video clip for the BeatlesExplorer user interface prototype created for AMR’08.
Bibtex
@phdthesis{stober2011thesis, author = {Sebastian Stober}, title = {Adaptive Methods for User-Centered Organization of Music Collections}, address = {Magdeburg, Germany}, month = {Nov}, school = {Otto-von-Guericke-University}, year = {2011}, note = {published by Dr. Hut Verlag, ISBN 978-3-8439-0229-8}, url = {http://www.dr.hut-verlag.de/978-3-8439-0229-8.html} }