Conference/Proceedings16th European Signal Processing Conference, EUSIPCO 2008, Proceedings, Lausanne, Switzerland
Start date25.08.2008
End date29.08.2008
AddressLausanne, Switzerland
OrganisationEuropean Association for Signal Processing (EURASIP), Swiss Federal Institute of Technology Lausanne (EPFL)
EditorJ.-Ph. Thiran, P. Vandergheynst, R. Reilly
VolumeAugust 2008
Author(s)Sebastian Wegener, Martin Haller, Juan José Burred, Thomas Sikora, Slim Essid, Gaël Richard
TitleOn the Robustness of Audio Features for Musical Instrument Classification
AbstractWe examine the robustness of several audio features applied
exemplarily to musical instrument classification. For this
purpose we study the robustness of 15 MPEG-7 Audio Low-
Level Descriptors and 13 further spectral, temporal, and perceptual features against four types of signal modifications: low-pass filtering, coding artifacts, white noise, and reverberation. The robustness of the 120 feature coefficients obtained is evaluated with three different methods: comparison of rankings obtained by feature selection techniques, qualitative evaluation of changes in statistical parameters, and classification experiments using Gaussian Mixture Models(GMMs). These experiments are performed on isolated notes of 14 musical instrument classes.
Key wordsrobust audio features, evaluation, musical instrument classification, MPEG-7, filtering, gaussian mixture models, gmms)
NoteOral presentation