2026-04-13T07:34:51Zhttps://recercat.cat/oai/requestoai:recercat.cat:10230/437412025-12-26T11:21:35Zcom_2072_6col_2072_452952
RECERCAT
author
Miron, Marius
author
Carabias Orti, Julio J.
author
Janer Mestres, Jordi
2020-02-28T09:51:30Z2020-02-28T09:51:30Z2015
Comunicació presentada a la 16th International Society for Music Information Retrieval Conference (ISMIR 2015), celebrada els dies 26 a 30 d'octubre de 2015 a Màlaga, Espanya.Signal decomposition methods such as Non-negative Matrix
Factorization (NMF) demonstrated to be a suitable approach
for music signal processing applications, including
sound source separation. To better control this decomposition,
NMF has been extended using prior knowledge and
parametric models. In fact, using score information considerably
improved separation results. Nevertheless, one
of the main problems of using score information is the misalignment
between the score and the actual performance.
A potential solution to this problem is the use of audio to
score alignment systems. However, most of them rely on a
tolerance window that clearly affects the separation results.
To overcome this problem, we propose a novel method to
refine the aligned score at note level by detecting both, onset
and offset for each note present in the score. Note refinement
is achieved by detecting shapes and contours in
the estimated instrument-wise time activation (gains) matrix.
Decomposition is performed in a supervised way, using
training instrument models and coarsely-aligned score
information. The detected contours define time-frequency
note boundaries, and they increase the sparsity. Finally, we
have evaluated our method for informed source separation
using a dataset of Bach chorales obtaining satisfactory results,
especially in terms of SIR.This work was supported by the European Commission,
FP7 (Seventh Framework Programme), STREP project, ICT-
2011.8.2 ICT for access to cultural resources, grant agreement
No 601166. Phenicx Project
© Marius Miron, Julio Jose Carabias-Orti, Jordi Janer. Licensed under a Creative Commons Attribution 4.0 International License
(CC BY 4.0). Attribution: Marius Miron, Julio Jose Carabias-Orti, Jordi Janer. “Improving score-informed source separation for classical
music through note refinement”, 16th International Society for Music Information Retrieval Conference, 2015. https://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess
Source separation
Improving score-informed source separation for classical music through note refinement
info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/publishedVersion