TY - THES T1 - Informed Source Separation for Multiple Instruments of Similar Timbre T2 - Music Technology Group, Universitat Pompeu Fabra Y1 - 2013 A1 - López, Jakue KW - source Separation KW - Timbre modelling AB -

This Master’s thesis focuses on the challenging task of separating the musical audio sources with instruments of similar timbre. We address the case in which external pitch information to assist the separation process is available. This information is provided to the source / filter model, which is embedded in a Non-Negative Matrix Factorization (NMF) framework that processes the audio input spectrogram. Different state of the art literature methods are inspected and extended. As an extension to these, two new separation methods are proposed, the Multi-Excitation and Single Filter Instantaneous Mixture Model and the Multi-Excitation and Multi-Filter Instantaneous Mixture Model. The use of dedicated source and filter decomposition for each instrument is proposed. In addition, we introduce the use of timbre models in the separation process. Timbre models are previously trained on isolated instrument recordings. The methods are compared with the BSS Eval and PEASS evaluation toolkits over an existing dataset. Promising results obtained in the conducted experiments, which shows that this is a path to be further investigated.

JF - Music Technology Group, Universitat Pompeu Fabra VL - Master in Sound and Music Computing UR - http://mtg.upf.edu/system/files/publications/Jakue-Lopez-Master-Thesis-2013.pdf ER - TY - CONF T1 - Study of regularizations and constraints in NMF-based drums monaural separation T2 - International Conference on Digital Audio Effects Conference (DAFx-13) Y1 - 2013 A1 - Marxer, R. A1 - Janer, J. KW - drums KW - NMF KW - source Separation AB -

Drums modelling is of special interest in musical source separation because of its widespread presence in western popular music. Current research has often focused on drums separation without specifically modelling the other sources present in the signal. This paper presents an extensive study of the use of regularizations and constraints to drive the factorization towards the separation between percussive and non-percussive music accompaniment. The proposed regularizations control the frequency smoothness of the basis components and the temporal sparseness of the gains. We also evaluated the use of temporal constraints on the gains to perform the separation, using both ground truth manual annotations (made publicly available) and automatically extracted transients. Objective evaluation of the results shows that, while optimal regularizations are highly dependent on the signal, drum event position contains enough information to achieve a high quality separation.

JF - International Conference on Digital Audio Effects Conference (DAFx-13) UR - http://dafx13.nuim.ie/papers/16.dafx2013_submission_16.pdf ER -