Music signal separation using supervised NMF with all-pole-model-based discriminative basis deformation

Nakajima, Hiroaki; Kitamura, Daichi; Takamune, Norihiro; Koyama, Shoichi; Saruwatari, Hiroshi; Takahashi, Yu; Kondo, Kazunobu

doi:10.1109/eusipco.2016.7760427

Cited by 4 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PSNMF forces F s and H to become uncorrelated by penalizing the semi-supervised factorization (equation ( 2)) with an orthogonality constraint [27]. Formally, the PSNMF resolves the following optimization problem [27,36] argmin…”

Section: Psnmfmentioning

confidence: 99%

Spectroscopic analysis improvement using convolutional neural networks

Saura

Gonzalez

Benkadda

et al. 2023

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

Removing noisy components of signals coming from edge tokamak plasmas, astrochemical organic matter or astronomical objects is one of the promising path to improve the underlying elements identification. Methods such as the penalized semi-supervised non negative matrix factorization (PSNMF) used to extract such prominent elements perform well on complex signals. However, it's results' confidence decreases as the noise increases. In this context, we have tried to address this limitation by removing part of the undesired noise in atomic spectra using artificial intelligence (AI) method based on convolutional neural networks (CNN). More specifically, we have tested different architectures of CNN classically used in denoising task: residual CNNs and auto-encoders, to benchmark their respective denoising capacity. The dataset used is made of atom and ion spectra extracted from the NIST Atomic Spectra Database. In the case of ions, we have considered several degrees of ionization. The synthetic added noise is generated from a typical experimental noise profile randomly modified for each signal. Performance of each AI-based noise remover is measured by analysing the increase of the element identification precision obtained by the PSNMF. Auto-encoders and residual CNN are both suitable to remove the undesired noise and increase the PSNMF efficiency even for noise-prevailing signals. In this particular case, the auto-encoder architecture seems to be globally more accurate and should be selected when considering noisy multi-element atomic spectra.

show abstract

Section: Psnmfmentioning

confidence: 99%

Spectroscopic analysis improvement using convolutional neural networks

Saura

Gonzalez

Benkadda

et al. 2023

J. Phys. D: Appl. Phys.

View full text Add to dashboard Cite

show abstract

“…Bisot et al [43] applied supervised NMF to acoustic scene classification and obtained rather good performance. Sprechmann et al [44] and Weninger et al [81] solved the audio source separation with supervised NMF, while Nakajima et al [82] and Kitamura et al [83] adopted supervised NMF for music signal separation.…”

Section: Speech Recognitionmentioning

confidence: 99%

Recent Advances in Supervised Dimension Reduction: A Survey

Chao

Luo

Ding

2019

MAKE

View full text Add to dashboard Cite

Recently, we have witnessed an explosive growth in both the quantity and dimension of data generated, which aggravates the high dimensionality challenge in tasks such as predictive modeling and decision support. Up to now, a large amount of unsupervised dimension reduction methods have been proposed and studied. However, there is no specific review focusing on the supervised dimension reduction problem. Most studies performed classification or regression after unsupervised dimension reduction methods. However, we recognize the following advantages if learning the low-dimensional representation and the classification/regression model simultaneously: high accuracy and effective representation. Considering classification or regression as being the main goal of dimension reduction, the purpose of this paper is to summarize and organize the current developments in the field into three main classes: PCA-based, Non-negative Matrix Factorization (NMF)-based, and manifold-based supervised dimension reduction methods, as well as provide elaborated discussions on their advantages and disadvantages. Moreover, we outline a dozen open problems that can be further explored to advance the development of this topic.

show abstract