NOTE:
Elias Pampalk is not working at OFAI anymore. These pages are no longer updated and kept for archiving purposes only. For any further information, please visit Elias Pampalk's personal webpage.


Elias Pampalk, Dr.techn.

Austrian Research Institute
for Artificial Intelligence (OFAI)


Freyung 6/6
A-1010 Vienna, Austria



EMAIL  elias.pampalk@ofai.at
WEB  www.ofai.at/~elias.pampalk  

PHONE  (+43-1) 533 6112 - 19  
FAX  (+43-1) 533 6112 - 77  





> ELIAS | PROJECTS | PUBLICATIONS | LINKS


PROJECTS


SIMAC: Semantic Interaction with Music Audio Contents
SIMAC is a project funded by the European Commission. The main task is the development of prototypes for the exploration, recommendation and retrieval of music. SIMAC is organized by MTG in collaboration with QMUL, Matrix Data, Philips Research, and ÖFAI.

Keywords: music descriptor extraction, playlist generation, information visualization, music archives.

Computer-Based Music Research: AI Models of Musical Expression
The goal of this project is to use Artificial Intelligence methods to study the phenomenon of expressive music performance. The focus of the project is on developing and using machine learning and data mining methods for the analysis of expressive performance data. The goal is to gain a deeper understanding of this complex domain of human competence and to contribute new methods to the (relatively new) branch of musicology that tries to develop quantitative models and theories of musical expression.
This project was featured in Wired Magazine (Sept 2001, pp 100-112) and in Der Spiegel (June 2002, No. 23, pp 174-176).

Keywords: identification of distinctive subsequences in multivariate time series.

MA Toolbox for Matlab
A collection of similarity measures for audio. The toolbox implements the approaches presented by B. Logan & A. Salomon, J.-J. Aucouturier & F. Pachet, as well of some of our own.

Keywords: content-based music analysis, feature extraction, Matlab.

GHSOM Toolbox for Matlab
The GHSOM (Growing Hierarchical Self-Organizing Map) Toolbox includes functions to train, visualize, and label a GHSOM. Furthermore, several demonstrations explain basic characteristics, parameters, the relationship to the SOM, and possible applications.

Keywords: hierarchical clustering, growing hierarchical self-organizing maps, Matlab.

Islands of Music: Analysis, Organization, and Visualization of Music Archives
Islands of Music are a graphical user interface to music archives based on a metaphor of geographic maps where islands represent musical genres or styles. Pieces of music are automatically placed on the map according to their sound characteristics which are determined using psychoacoustic models focusing on the dynamics of loudness fluctuations in specific frequency bands.

Keywords: psychoacoustic models, perceived similarity, content-based music analysis, music retrieval, digital libraries, MP3.

SDH Toolbox for Matlab
The SDH (Smoothed Data Histogram) Toolbox includes functions for cluster visualization with Self-Organizing Maps. The SDH is the front-end (user interface) to the system developed in the Islands of Music project.

Keywords: explorative data analysis, data visualization, clustering, cluster visualization, self-organizing maps, density estimation, Matlab.



last updated: July 29th, 2006 by elias