TU Berlin

Communication Systems GroupScientific Publications

Page Content

to Navigation

Scientific Publications

Monaural Source Separation from Musical Mixtures Based on Time-Frequency Timbre Models
Citation key 1086Burred2007
Author Juan José Burred and Thomas Sikora
Title of Book International Conference on Music Information Retrieval (ISMIR 2007)
Year 2007
Address Vienna, Austria
Month sep
Abstract We present a system for source separation from monaural musical mixtures based on Sinusoidal Modeling and on a library of timbre models trained a priori. The models, which rely on Principal Component Analysis, serve as time-frequency probabilistic templates of the spectral envelope. They are used to match groups of sinusoidal tracks and assign them to a source, as well as to reconstruct overlapping partials. The proposed method does not make any assumptions on the harmonicity of the sources, and does not require a previous multipitch estimation stage. Since the timbre matching stage detects the instruments present on the mixture, the system can also be used for classification and segmentation.
Link to publication Download Bibtex entry


Quick Access

Schnellnavigation zur Seite über Nummerneingabe