Contact:
Wiener Wissenschafts-, Forschungs- und Technologiefonds
Schlickgasse 3/12
A-1090 Wien
Tel: +43 1 402 31 43 - 10
Fax: +43 1 402 31 43 - 20
office{at}mail.wwtf.at
www.wwtf.at
Audio-Miner. Mathematical Signal Analysis and Modeling for Manipulation of Sound Objects
| Project type: | Research Project |
| Programme: | Mathematics and... |
| Call: | Mathematik und ... Call 2009 |
| Start: | 01.01.2010 |
| Duration: | 3,00 years |
| Grant awarded: | 483.700 € |
| Keywords: | Adaptive signal representations, sparse coefficients, music information retrieval, audio analysis, time-frequency masking |
Monika Dörfler
University of Vienna
Department of Mathematics
| Project partners: | Arthur Flexer (Austrian Research Institute for Artificial Intelligence, OFAI) Simon Dixon (Queen Mary University London, Centre for Digital Music) Bruno Torrésani (Université de Provence, Centre de Mathématique et d'Informatique) |
An important open research question in Music Information Retrieval (MIR) is the extraction of sound objects (e.g. a guitar chord, the beat of a bass drum, the bark of a dog) from polyphonic audio. Recent theoretical advances in mathematical signal processing indicate the possibility of a decisive improvement in identifying and extracting sound objects directly from the time-frequency plane. These mined sound objects can then automatically be organized into perceptually meaningful and easy to navigate sound libraries using the latest innovations in MIR based music similarity. Together this will form the core of a powerful new toolkit for audio manipulation with widespread applicability in fields like Sound Design, Computational Auditory Scene Analysis, Artefact Reduction or Audio Database Organisation.
| Project's website: | www.ofai.at/research/impml/projects/audi... |
