DELOS is a Network of Excellence on Digital Libraries partially funded by the European Commission in the frame of the Information Society Technologies (IST) Programme. It started on 1st January 2004 with a duration of 48 months and includes 55 members. The DELOS network is conducting a joint program of activities aimed at integrating and coordinating the ongoing research activities of the major European teams working in Digital Library related areas with the goal of developing the next generation Digital Library technologies. DELOS also aims at disseminating knowledge of digital library technologies to many diverse application domains. Our group at TU Vienna-IFS concentrated efforts on Audio/Visual and Non-traditional Objects, Digital Library Architecture, User Interfaces & Visualization, and Digital Preservation.

Project website: http://www.delos.info

MUSCLE is a Network of Excellence on Multimedia Understanding through Semantics, Computation and Learning, partially funded by the European Commission in the 6h framework programme from 2004 to 2008. The network aims at establishing and fostering closer collaboration between research groups in multimedia datamining and machine learning. It integrates the expertise of over 40 research groups working on image and video processing, speech, audio and text analysis, statistics and machine learning, in order to explore the full potential of statistical learning and cross-modal interaction for the (semi-)automatic generation of robust meta-data with high semantic value for multimedia documents.
Work package 4 on Content Description for Audio, Speech and Text is led by Andreas Rauber.

Project website: http://www.muscle-noe.org

Project brochure

IMPACT (Improving Music genre classification Performance by a novel Approach of Combining audio and symbolic music descriptors using a Transcription system) is a bilateral project, funded by the Austrian Academic Exchange Service, between our group and the Pattern Recognition and Artificial Intelligence Group (GRFIA) at the University of Alicante, Spain. The main goal of the project collaboration is to build a new audio and music genre classification system joining audio features with symbolic descriptors by using a transcription system in order to improve and outperform previous audio-only based approaches. The outcome of the project will be a system that reliably categorizes unlabeled pieces of music into a user-definable set of genre categories. Moreover, this joint approach can subsequently also be used to address further problems such as artist identification, duplicate finding or plagiarism detection.