Filters








27,584 Hits in 6.7 sec

Noise-to-mask ratio minimization by weighted non-negative matrix factorization

Joonas Nikunen, Tuomas Virtanen
2010 2010 IEEE International Conference on Acoustics, Speech and Signal Processing  
This paper proposes a novel algorithm for minimizing the perceptual distortion in non-negative matrix factorization (NMF) based audio representation.  ...  We formulate the noise-to-mask ratio audio quality criterion in a form where it can be used in NMF and propose an algorithm for optimizing the criterion.  ...  CONCLUSION We have proposed a method for minimizing the noise-to-mask ratio using non-negative matrix factorization.  ... 
doi:10.1109/icassp.2010.5496264 dblp:conf/icassp/NikunenV10 fatcat:6kfq52vgabhxfdykdcbshgmpiu

Weighted Nmf For High-Resolution Mass Spectrometry Analysis

Rémi Dubroca, Christophe Junot, Antoine Souloumiac
2012 Zenodo  
This weighting matrix is non negative and takes its values between 0 and 1.  ...  the Weighted Nonnegative Matrix Factorization (WNMF).  ... 
doi:10.5281/zenodo.42936 fatcat:5qpgerpxjrb6bfz5x3ct5bzdja

Ghost Projection [article]

David Ceddia, David M. Paganin
2021 arXiv   pre-print
We explore three means of achieving ghost projection: (i) weighting each random mask, namely selecting its exposure time, according to its correlation with a desired image, (ii) selecting a subset of random  ...  Ghost imaging is a developing imaging technique that employs random masks to image a sample.  ...  Pseudo-correlation Weighted Ghost Projection Suppose we wish to project a desired image I ij , up to an additive constant, using a non-negative randommatrix basis R ijk weighted by non-negative coefficients  ... 
arXiv:2109.01666v1 fatcat:jwcjaghgevd3tc3dqboshsnxbi

Restoration Of Audio Documents With Low Snr: A Nmf Parameter Estimation And Perceptually Motivated Bayesian Suppression Rule

Giuseppe Cabras, Sergio Canazza, Pier Luca Montessoro, Roberto Rinaldo
2010 Proceedings of the SMC Conferences  
(Abstract to follow)  ...  A recent approach to separate an acoustic source is provided by Non-negative Matrix Factorization (NMF).  ...  The proposed approach tries to solve this problem with a solution based on an extended Non-negative Matrix Factorization algorithm and prior knowledge on interference.  ... 
doi:10.5281/zenodo.849819 fatcat:atduuqf6rzhi3cnck2hj2fcxje

An Overcomplete Wdft Sinusoidal Basis For Perceptually Motivated Speech Enhancement

Adam Borowicz, Alexander Petrovsky
2005 Zenodo  
Noise attenuation factor (NA) defined as the mean ratio of the input to output noise power, was used to evaluate the suppression capabilities of tested systems.  ...  ) To calculate weighting coefficients the estimates of the masking threshold ( ) TT R ω and noise power spectral density ( ) nn R ω are only needed.  ... 
doi:10.5281/zenodo.38995 fatcat:5ealk6ttgbhixggqpt3w2nzhxu

INTERPOLATING MASKED WEAK-LENSING SIGNAL WITH KARHUNEN-LOÈVE ANALYSIS

J. T. VanderPlas, A. J. Connolly, B. Jain, M. Jarvis
2011 Astrophysical Journal  
We find that the KL procedure not only minimizes the bias due to masked regions in the field, it also reduces spurious peak counts from shape noise by a factor of ~ 3 in the cosmologically sensitive regime  ...  We develop a method to use two dimensional KL eigenmodes of shear to interpolate noisy shear measurements across masked regions.  ...  The simulation used to produce the catalogs is one of the Carmen simulations, a 1 Gpc simulation run by M. Busha as part of the Las-Damas project.  ... 
doi:10.1088/0004-637x/744/2/180 fatcat:y4nlbusjjzflllm3epp43guexi

Itakura-Saito Divergence Non Negative Matrix Factorization with Application to Monaural Speech Separation

A. Adewusi, K. A., A. R.
2016 International Journal of Computer Applications  
However, many solutions have been developed to achieve clean separation based on Non-Negative Matrix Factorization (NMF).  ...  Besides that, Source to distortion ratio (SDR) and Source to Artifact Ratio (SAR) were found to be higher when compared with NMF algorithms with Kullback-Leibler and Euclidean divergences.  ...  Various Non-Negative Matrix factorization based techniques have been widely employed to achieve separation in this regime and these include shifted NMF [5] Non-negative matrix factorization (NMF) has  ... 
doi:10.5120/ijca2016912112 fatcat:tiu2j4lz7rbxnnox625xbxg5iu

Audio Restoration Of Solo Guitar Excerpts Using A Excitation-Filter Instrument Model

J. Parras-Moral, F. J. Cañadas-Quesada, P. Vera-Candeas, N. Ruiz-Reyes
2013 Proceedings of the SMC Conferences  
(Abstract to follow)  ...  in an augmented non-negative matrix factorization (NMF) algorithm.  ...  In the case of magnitude spectra, the parameters are restricted to be non-negative, then, a common way to compute the factorization is to minimize the reconstruction error between the observed spectrogram  ... 
doi:10.5281/zenodo.850219 fatcat:dgwa6vlqcne67movyxqvvyeuly

3D Acoustic Mapping in Automotive Wind Tunnel: Algorithm and Problem Analysis on Simulated Data

Gianmarco Battista, Paolo Chiariotti, Milena Martarelli, Paolo Castellini, Claudio Colangeli, Karl Janssens
2021 Applied Sciences  
In fact, the car is a 3D object that radiates noise from different parts simultaneously, involving different noise generation mechanisms such as tire noise and aerodynamic noise.  ...  Such a controlled simulation environment, by contrast to a purely experimental case, enables accurate assessment of both the localization and quantification performance of the proposed method.  ...  Acknowledgments: The authors wish to thank and acknowledge the work of the Pininfarina team during the EU project WENEMOR (Grant agreement no: 278419.  ... 
doi:10.3390/app11073241 fatcat:qb6dhndu5va5tft7xdftts7bty

Single channel speech music separation using nonnegative matrix factorization and spectral masks

Emad M. Grais, Hakan Erdogan
2011 2011 17th International Conference on Digital Signal Processing (DSP)  
The proposed algorithm uses training data of speech and music signals with nonnegative matrix factorization followed by masking to separate the mixed signal.  ...  A single channel speech-music separation algorithm based on nonnegative matrix factorization (NMF) with spectral masks is proposed in this work.  ...  NON-NEGATIVE MATRIX FACTORIZATION Non-negative matrix factorization is an algorithm that is used to decompose any nonnegative matrix into a nonnegative basis vectors matrix and a nonnegative weights matrix  ... 
doi:10.1109/icdsp.2011.6004924 fatcat:ghkkqhpps5fefixodba52hn7ra

Estimating nonnegative matrix model activations with deep neural networks to increase perceptual speech quality

Donald S. Williamson, Yuxuan Wang, DeLiang Wang
2015 Journal of the Acoustical Society of America  
On the other hand, nonnegative matrix factorization (NMF) addresses separation by linearly combining basis vectors from speech and noise models to approximate noisy speech.  ...  A deep neural network then approximates clean speech by estimating activation weights from the ratio-masked speech, where the weights linearly combine elements from a NMF speech model.  ...  ACKNOWLEDGMENTS This research was supported in part by an AFOSR grant (No. FA9550-12-1-0130), an NIDCD grant (No. R01 DC012048), and the Ohio Supercomputer Center.  ... 
doi:10.1121/1.4928612 pmid:26428778 pmcid:PMC5392055 fatcat:2ydwgowujfbh7a4f5jaziqtmva

Singing-voice separation from monaural recordings using robust principal component analysis

Po-Sen Huang, Scott Deeann Chen, Paris Smaragdis, Mark Hasegawa-Johnson
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Moreover, we examine the separation result by using a binary time-frequency masking method.  ...  Music accompaniment can be assumed to be in a low-rank subspace, because of its repetition structure; on the other hand, singing voices can be regarded as relatively sparse within songs.  ...  (SIR), Source to Artifacts Ratio (SAR), and Source to Distortion Ratio (SDR) by BSS-EVAL metrics [14] .  ... 
doi:10.1109/icassp.2012.6287816 dblp:conf/icassp/HuangCSH12 fatcat:ftnv7ldkzrbdvfpcg6a7ur7apu

Robust Infrared Superpixel Image Separation model for small target detection

Zujing Yan, Yunhong Xin, Lili Liu, Ruiheng Su, Dongbo Chen
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Second, an outlier superpixel masking (OSM) model is proposed to perform accurate identification and masking of the outlier superpixels with highly heterogeneous backgrounds, thus minimizing false alarm  ...  Finally, a singular value truncation strategy with entropy weighted sparse factor (SVT-EW) is proposed to implement the final target extraction, which assigns specific sparsity weights for small infrared  ...  A Non-negative IPI model based on Partial Sum minimization of singular values (NIPPS) [38] introduces additional non-negative constraints and singular value partial sum minimization to make targeted  ... 
doi:10.1109/jstars.2021.3116965 fatcat:2m3nwjjarvftpirljqaacmtr2m

Robust Matrix Factorization with Grouping Effect [article]

Haiyan Jiang, Shuyu Li, Luwei Zhang, Haoyi Xiong, Dejing Dou
2021 arXiv   pre-print
In addition, GRMF can be easily extended to the Non-negative Matrix Factorization (NMF) settings.  ...  Although many techniques have been applied to matrix factorization (MF), they may not fully exploit the feature structure.  ...  The Robust Non-negative Matrix Factorization (RNMF) (Zhang et al., 2011) decomposes the non-negative data matrix as the summation of one sparse error matrix and the product of two non-negative matrices  ... 
arXiv:2106.13681v2 fatcat:l2vxbs3tcrgyhdlkcfmtlrllsq

Harmonic-Percussive Source Separation of Polyphonic Music by Suppressing Impulsive Noise Events

Gurunath Reddy M, K. Sreenivasa Rao, Partha Pratim Das
2018 Interspeech 2018  
In this work, we have proposed Affine and Gain masking methods to separate the harmonic and percussive components to achieve minimal spectral leakage.  ...  The significant advantage of the proposed method is that it minimizes the artifacts in the separated signal spectrograms.  ...  The authors would like to thank Google for supporting first author PhD under Google India PhD Fellowship program.  ... 
doi:10.21437/interspeech.2018-1310 dblp:conf/interspeech/MRD18 fatcat:jez44awz5baxhnflxfjjrqlwz4
« Previous Showing results 1 — 15 out of 27,584 results