Constrained non-negative matrix factorization for score-informed piano music restoration

Canadas-Quesada, F.; Martinez-Munoz, D.; Ruiz-Reyes, N.; Carabias-Orti, Julio J.; Cabañas-Molero, Pablo

doi:10.1016/j.dsp.2016.01.004

Cited by 19 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The noise related problems in the dataset were presented in [30]. We remove the noise in the recordings with the score-informed method in [39], which relies on learned noise spectral patters. The main difference is that we rely on a manually annotated score, while in [39] the score is assumed to be misaligned, so further regularization is included to ensure that only certain note combinations in the score occur.…”

Section: Dataset Denoisingmentioning

confidence: 99%

Score-Informed Source Separation for Multichannel Orchestral Recordings

Miron

Carabias-Orti

Bosch

et al. 2016

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

This paper proposes a system for score-informed audio source separation for multichannel orchestral recordings. The orchestral music repertoire relies on the existence of scores. Thus, a reliable separation requires a good alignment of the score with the audio of the performance. To that extent, automatic score alignment methods are reliable when allowing a tolerance window around the actual onset and offset. Moreover, several factors increase the difficulty of our task: a high reverberant image, large ensembles having rich polyphony, and a large variety of instruments recorded within a distant-microphone setup. To solve these problems, we design context-specific methods such as the refinement of score-following output in order to obtain a more precise alignment. Moreover, we extend a close-microphone separation framework to deal with the distant-microphone orchestral recordings. Then, we propose the first open evaluation dataset in this musical context, including annotations of the notes played by multiple instruments from an orchestral ensemble. The evaluation aims at analyzing the interactions of important parts of the separation framework on the quality of separation. Results show that we are able to align the original score with the audio of the performance and separate the sources corresponding to the instrument sections.

show abstract

Section: Dataset Denoisingmentioning

confidence: 99%

Score-Informed Source Separation for Multichannel Orchestral Recordings

Miron

Carabias-Orti

Bosch

et al. 2016

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…Traditionally, NMF methods using score information enforced the sparsity by imposing certain constraints on the basis functions S and/or the time-varying gains A. For example, the musical structure of the score can be exploited to penalize activations of notes or combinations of notes which are not present in the score [34,55]. Additionally, if the score is pre-aligned with the interpretation, it is possible to set to zero those gains associated to the basis functions of non-active notes.…”

Section: Score-informed Constraintsmentioning

confidence: 99%

Online/offline score informed music signal decomposition: application to minus one

Muñoz-Montoro

Carabias-Orti

Canadas-Quesada

et al. 2019

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

In this paper, we propose a score-informed source separation framework based on non-negative matrix factorization (NMF) and dynamic time warping (DTW) that suits for both offline and online systems. The proposed framework is composed of three stages: training, alignment, and separation. In the training stage, the score is encoded as a sequence of individual occurrences and unique combinations of notes denoted as score units. Then, we proposed a NMF-based signal model where the basis functions for each score unit are represented as a weighted combination of spectral patterns for each note and instrument in the score obtained from a trained a priori over-completed dictionary. In the alignment stage, the time-varying gains are estimated at frame level by computing the projection of each score unit basis function over the captured audio signal. Then, under the assumption that only a score unit is active at a time, we propose an online DTW scheme to synchronize the score information with the performance. Finally, in the separation stage, the obtained gains are refined using local low-rank NMF and the separated sources are obtained using a soft-filter strategy. The framework has been evaluated and compared with other state-of-the-art methods for single channel source separation of small ensembles and large orchestra ensembles obtaining reliable results in terms of SDR and SIR. Finally, our method has been evaluated in the specific task of acoustic minus one, and some demos are presented. which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.f ,t X(f , t)log X(f ,t) X(f ,t)− X(f , t) +X(f , t) β = 1 f ,t X(f ,t) X(f ,t)+ log X(f ,t) X(f ,t)

show abstract

“…We have chosen a relatively long piano part ( [26], that lasts 624 seconds) and obtained its spectrogram. (The data matrix can be downloaded from http://www.inco2.upv.es/software.php; the procedure to obtain the spectrogram from an audio file is the described in [27]). The procedure used to obtain the spectrogram causes that each second corresponds to 43 new columns.…”

Section: Real Application: Automatic Music Transcriptionmentioning

confidence: 99%

Updating/downdating the NonNegative Matrix Factorization

Juan

Vidal

Garcia-Mollá

2017

Journal of Computational and Applied Mathematics

View full text Add to dashboard Cite

The Non-Negative Matrix Factorization (NNMF) is a recent numerical tool that, given a non-negative data matrix, tries to obtain its factorization as the approximate product of two nonnegative matrices. Nowadays, this factorization is being used in many science fields; in some of these fields, real-time computation of the NNMF is required. In some scenarios, all data is not initially available and when new data (as new rows or columns) becomes available the NNMF must be recomputed. Recomputing the whole factorization every time is very costly and not suitable for real time applications. In this paper we propose several algorithms to update the NNMF factorization taking advantage of the previously computed factorizations, with similar error and lower computational cost.

show abstract

Constrained non-negative matrix factorization for score-informed piano music restoration

Cited by 19 publications

References 16 publications

Score-Informed Source Separation for Multichannel Orchestral Recordings

Score-Informed Source Separation for Multichannel Orchestral Recordings

Online/offline score informed music signal decomposition: application to minus one

Updating/downdating the NonNegative Matrix Factorization

Contact Info

Product

Resources

About