Ing. Petr Tichavský, DSc.

Biography
Publication list
Petr Tichavský graduated from the Faculty of Nuclear Sciences and Physical Engineering (FJFI) at the Czech Technical University (CTU) in Prague, 1982-1987, majoring in mathematical engineering.
He already started to work at UTIA in the second year of his study as a student researcher, under the supervision of prof. Vošvrda. After completing one year of military service, he started his postgraduate studies at UTIA, which he completed in 1992 by obtaining the degree of CSc in theoretical cybernetics. Since then, he has been working as a researcher at this institute in the Department of Stochastic Informatics. In 1994-1995 he completed a 10-month internship at Yale University in the USA, supported by a Fulbright scholarship.
In 2018 P. Tichavský defended his "Doctor of Science" thesis at the Czech Academy of Sciences and received the title of DSc. (research professor). Professionally, P. Tichavský cooperated with FJFI CTU, where he was a supervisor of several students. The most important student with whom P. Tichavský collaborated is the current Prof. Koldovský at the Technical University of Liberec.
P. Tichavsky has four grown-up children and two granddaughters. He lives with his wife and two youngest sons in Prague. He is a member of the Christian Fellowship in Prague.
Books and chapters
- Improved variants of the FastICA algorithm, Advances in Independent Component Analysis and Learning Machines, p. 53-74, Eds: Bingham Ella, Kaski Samuel, Laaksonen Jorma, Lampinen Jouko Download DOI: 10.1016/B978-0-12-802806-3.00002-6 [2015] :
Journal articles
- Parameter estimation in cyclic plastic loading, Acta Mechanica Download Download DOI: 10.1007/s00707-025-04385-8 [2025] :
- Optimizing the Order of Modes in Tensor Train Decomposition, IEEE Signal Processing Letters 32 3 (2025), p. 1361-1365 Download Download DOI: 10.1109/LSP.2025.3552005 [2025] :
- Grid-based Bayesian Filters with Functional Decomposition of Transient Density, IEEE Transactions on Signal Processing 71 2 (2023), p. 92-104 Download Download DOI: 10.1109/TSP.2023.3240359 [2023] :
- Double Nonstationarity: Blind Extraction of Independent Nonstationary Vector/Component from Nonstationary Mixtures - Algorithms, IEEE Transactions on Signal Processing 70 1 (2022), p. 5102-5116 Download Download DOI: 10.1109/TSP.2022.3216106 [2022] :
- Dynamic Independent Component/Vector Analysis: Time-Variant Linear Mixtures Separable by Time-Invariant Beamformers, IEEE Transactions on Signal Processing 69 1 (2021), p. 2158-2173 Download Download DOI: 10.1109/TSP.2021.3068626 [2021] :
- Krylov-Levenberg-Marquardt Algorithm for Structured Tucker Tensor Decompositions, IEEE Journal on Selected Topics in Signal Processing 15 3 (2021), p. 550-559 Download Download DOI: 10.1109/JSTSP.2021.3059521 [2021] :
- Cramér-Rao Bounds for Complex-Valued Independent Component Extraction: Determined and Piecewise Determined Mixing Models, IEEE Transactions on Signal Processing 68 10 (2020), p. 5230-5243 Download Download DOI: 10.1109/TSP.2020.3022827 [2020] :
- Performance Bounds for Complex-Valued Independent Vector Analysis, IEEE Transactions on Signal Processing 68 1 (2020), p. 4258-4267 Download Download DOI: 10.1109/TSP.2020.3009507 [2020] :
- Tensor Networks for Latent Variable Analysis: Novel Algorithms for Tensor Train Approximation, IEEE Transactions on Neural Networks and Learning Systems 31 11 (2020), p. 4622-4636 Download Download DOI: 10.1109/TNNLS.2019.2956926 [2020] :
- Sensitivity in tensor decomposition, IEEE Signal Processing Letters 26 11 (2019), p. 1653-1657 Download Download DOI: 10.1109/LSP.2019.2943060 [2019] :
- Error Preserving Correction: A Method for CP Decomposition at a Target Error Bound, IEEE Transactions on Signal Processing 67 5 (2019), p. 1175-1190 Download Download DOI: 10.1109/TSP.2018.2887192 [2019] :
- Gradient Algorithms for Complex Non-Gaussian Independent Component/Vector Extraction, Question of Convergence, IEEE Transactions on Signal Processing 67 4 (2019), p. 1050-1064 Download Download DOI: 10.1109/TSP.2018.2887185 [2019] :
- Non-orthogonal tensor diagonalization, Signal Processing 138 1 (2017), p. 313-320 Download DOI: 10.1016/j.sigpro.2017.04.001 [2017] :
- Numerical CP Decomposition of Some Difficult Tensors, Journal of Computational and Applied Mathematics 317 1 (2017), p. 362-370 Download DOI: 10.1016/j.cam.2016.12.007 [2017] :
- Partitioned Alternating Least Squares Technique for Canonical Polyadic Tensor Decomposition, IEEE Signal Processing Letters 23 7 (2016), p. 993-997 Download DOI: 10.1109/LSP.2016.2577383 [2016] :
- Tensor Deflation for CANDECOMP/PARAFAC - Part II: Initialization and Error Analysis, IEEE Transactions on Signal Processing 63 22 (2015), p. 5939-5950 Download DOI: 10.1109/TSP.2015.2458789 [2015] :
- Tensor Deflation for CANDECOMP/PARAFAC - Part I: Alternating Subspace Update Algorithm, IEEE Transactions on Signal Processing 63 22 (2015), p. 5924-5938 Download DOI: 10.1109/TSP.2015.2458785 [2015] :
- Joint Matrices Decompositions and Blind Source Separation, IEEE Signal Processing Magazine 31 3 (2014), p. 34-43 Download DOI: 10.1109/MSP.2014.2298045 [2014] :
- Probabilistic inference with noisy-threshold models based on a CP tensor decomposition, International Journal of Approximate Reasoning 55 4 (2014), p. 1072-1092 Download DOI: 10.1016/j.ijar.2013.12.002 [2014] :
- A Two-Stage MMSE Beamformer for Underdetermined Signal Separation, IEEE Signal Processing Letters 20 12 (2013), p. 1227-1230 Download DOI: 10.1109/LSP.2013.2285932 [2013] :
- Semi-Blind Noise Extraction Using Partially Known Position of the Target Source, IEEE Transactions on Audio Speech and Language Processing 21 10 (2013), p. 2029-2041 Download DOI: 10.1109/TASL.2013.2264674 [2013] :
- CANDECOMP/PARAFAC Decomposition of High-Order Tensors Through Tensor Reshaping, IEEE Transactions on Signal Processing 61 19 (2013), p. 4847-4860 Download DOI: 10.1109/TSP.2013.2269046 [2013] :
- Fast Alternating LS Algorithms for High Order CANDECOMP/PARAFAC Tensor Factorizations, IEEE Transactions on Signal Processing 61 19 (2013), p. 4834-4846 Download DOI: 10.1109/TSP.2013.2269903 [2013] :
- Cramér-Rao-Induced Bounds for CANDECOMP/ PARAFAC Tensor Decomposition, IEEE Transactions on Signal Processing 61 8 (2013), p. 1986-1997 Download DOI: 10.1109/TSP.2013.2245660 [2013] :
- Low Complexity Damped Gauss-Newton algorithms for CANDECOMP/PARAFAC, SIAM Journal on Matrix Analysis and Applications 34 1 (2013), p. 126-147 Download DOI: 10.1137/100808034 [2013] :
- Robust removal of short-duration artifacts in long neonatal EEG recordings using wavelet-enhanced ICA and adaptive combining of tentative reconstructions, Physiological Measurement 33 8 (2012), p. 39-49 Download DOI: 10.1088/0967-3334/33/8/N39 [2012] :
- Fast and accurate methods of independent component analysis: A survey, Kybernetika 47 3 (2011), p. 426-438 Download [2011] :
- Weight adjusted tensor method for blind separation of underdetermined mixtures of nonstationary sources, IEEE Transactions on Signal Processing 59 3 (2011), p. 1037-1047 Download DOI: 10.1109/TSP.2010.2096221 [2011] :
- Time-Domain Blind Separation of Audio Sources on the Basis of a Complete ICA Decomposition of an Observation Space, IEEE Transactions on Audio Speech and Language Processing 19 2 (2011), p. 406-416 Download DOI: 10.1109/TASL.2010.2049411 [2011] :
- Blind Separation of Piecewise Stationary NonGaussian Sources, Signal Processing 89 12 (2009), p. 2570-2584 Download DOI: 10.1016/j.sigpro.2009.04.021 [2009] :
- Fast Approximate Joint Diagonalization Incorporating Weight Matrices, IEEE Transactions on Signal Processing 57 3 (2009), p. 878-891 Download DOI: 10.1109/TSP.2008.2009271 [2009] :
- Corrections to "Performance Analysis of the FastICA Algorithm and Cramér-Rao Bounds for Linear Independent Component Analysis", IEEE Transactions on Signal Processing 56 4 (2008), p. 1715-1716 [2008] :
- A Hybrid Technique for Blind Separation of Non-Gaussian and Time-Correlated Sources Using a Multicomponent Approach, IEEE Transactions on Neural Networks 19 3 (2008), p. 421-430 [2008] :
- Blind instantaneous noisy mixture separation with best interference-plus-noise rejection, Lecture Notes in Computer Science 2007, p. 730-737 [2007] :
- Speed and accuracy enhancement of linear ICA techniques using rational nonlinear functions, Lecture Notes in Computer Science 2007 4666 (2007), p. 285-292 [2007] :
- Cramer-Rao-Induced Bound for Blind Separation of Stationary Parametric Gaussian Sources, IEEE Signal Processing Letters 14 6 (2007), p. 417-420 [2007] :
- A new pre-processing technique to enhance single-user-type DS-CDMA detectors in "blind" space-time rake receivers, IEEE Transactions on Wireless Communications 5 10 (2006), p. 2932-2944 [2006] :
- Efficient Variant of Algorithm FastICA for Independent Component Analysis Attaining the Cramer-Rao Lower Bound, IEEE Transactions on Neural Networks 17 5 (2006), p. 1265-1277 [2006] :
- Performance analysis of the FastICA algorithm and Cramér-Rao bounds for linear independent component analysis, IEEE Transactions on Signal Processing 54 4 (2006), p. 1189-1203 [2006] :
- Analytical derivation of finite-data-record performance of Wong-Lok-Lehnert-Zoltowski's DS-CDMA "blind" space-time receiver, IEEE Transactions on Signal Processing 53 4 (2005), p. 1485-1499 [2005] :
- Shifts of Seasons at the European Mid-latitudes: Natural Fluctuations Correlated with the North Atlantic Oscillations, Geophysical Research Letters 32 12 (2005) DOI: 10.1029/2005GL022838 [2005] :
- Human eye iris recognition using the mutual information, Optik 115 9 (2004), p. 399-404 [2004] :
- Quasi-fluid-mechanics-based quasi-Bayesian Cramer-Rao bounds for deformed towed-array direction finding, IEEE Transactions on Signal Processing 52 1 (2004), p. 36-47 [2004] :
- Optimal pairing of signal components separated by blind techniques, IEEE Signal Processing Letters 11 2 (2004), p. 119-122 [2004] :
- Near-field/far-field azimuth and elevation angle estimation using a single vector hydrophone, IEEE Transactions on Signal Processing 49 11 (2001), p. 2498-2510 [2001] :
- Filtering, predictive, and smoothing Cramér-Rao bounds for discrete-time nonlinear dynamic systems, Automatica 37 11 (2001), p. 1703-1716 [2001] :
- Cross-product algorithms for source tracking using an EM vector sensor, IEEE Transactions on Signal Processing 47 10 (1999), p. 2863-2867 [1999] :
- Multicomponent polynomial phase signal analysis using a tracking algorithm, IEEE Transactions on Signal Processing 47 5 (1999), p. 1390-1395 [1999] :
- Detection of influential points by convex hull volume minimization, Kybernetika 34 5 (1998), p. 515-534 [1998] :
- Posterior Cramér-Rao bounds for discrete-time nonlinear filtering, IEEE Transactions on Signal Processing 46 5 (1998), p. 1386-1396 [1998] :
- Large error recovery for a class of frequency tracking algorithms, International Journal of Adaptive Control and Signal Processing 12 5 (1998), p. 417-436 [1998] :
- Strong ergodicity conditions for the n-th order moment (cumulant) of multiple sinusoids, Signal Processing 65 2 (1998), p. 257-266 [1998] :
- Asymptotic noise gain of polynomial predictors, Signal Processing 62 2 (1997), p. 247-250 [1997] :
- Frequency rate estimation at high SNR, IEEE Transactions on Signal Processing 45 8 (1997), p. 2101-2105 [1997] :
- Comparative study of four adaptive frequency trackers, IEEE Transactions on Signal Processing 45 6 (1997), p. 1473-1484 [1997] :
- Recursive estimation of frequencies and frequency rates of multiple cisoids in noise, Signal Processing 58 2 (1997), p. 117-129 [1997] :
- Two algorithms for adaptive retrieval of slowly time-varying multiple cisoids in noise, IEEE Transactions on Signal Processing 43 5 (1995), p. 1116-1127 [1995] :
- Posterior Cramér-Rao Bound for adaptive harmonic retrieval, IEEE Transactions on Signal Processing 43 5 (1995), p. 1299-1302 [1995] :
- Statistical characterization of sample fourth-order cumulants of a noisy complex sinusoidal process, IEEE Transactions on Signal Processing 43 7 (1995), p. 1620-1630 [1995] :
- Adaptive filtering for periodic signal enhancement and tracking, International Journal of Adaptive Control and Signal Processing 8 5 (1994), p. 447-456 [1994] :
- High-SNR Asymptotics for Signal-Subspace Methods in Sinusoidal Frequency Estimation, IEEE Transactions on Signal Processing 41 7 (1993), p. 2448-2460 [1993] :
- Algorithms for and Geometrical Characterization of Solutions in the LMS and LTS Linear Regression, Computational Statistics Quarterly 6 2 (1991), p. 139-151 [1991] :
Other publications
- Tensor Train Approximation of Multivariate Functions, EUSIPCO 2024, p. 2262-2266 Download Download DOI: 10.23919/EUSIPCO63174.2024.10715191 [2024] :
- Active Fault Detection Based on Tensor Train Decomposition, IFAC-PapersOnLine. Volume 58, Issue 4 -12th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes SAFEPROCESS 2024, p. 676-681 Download Download DOI: 10.1016/j.ifacol.2024.07.297 [2024] :
- Tensor Chain Decomposition and Function Interpolation, Proceedings of the 22nd IEEE Statistical Signal Processing Workshop, p. 557-561 Download [2023] :
- Point-mass filter with functional decomposition of transient density and two-level convolution, IFAC-PapersOnLine. Volume 56, Issue 2 - 22nd IFAC World Congress, p. 7516-7520 Download DOI: 10.1016/j.ifacol.2023.10.509 [2023] :
- Point-Mass Filter with Decomposition of Transient Density, 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, p. 5752-5756 Download DOI: 10.1109/ICASSP43922.2022.9747607 [2022] :
- Canonical polyadic tensor decomposition with low-rank factor matrices, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), p. 4690-4694 Download DOI: 10.1109/ICASSP39728.2021.9414606 [2021] :
- Stable Low-Rank Tensor Decomposition for Compression of Convolutional Neural Network, ECCV 2020, p. 522-539, Eds: Vedaldi Andrea, Bischof Horst, Brox Thomas, Frahm Jan-Michael Download DOI: 10.1007/978-3-030-58526-6_31 [2020] :
- Weighted Krylov-Levenberg-Marquardt method for canonical polyadic tensor decomposition, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2020, p. 3917-3921 Download DOI: 10.1109/ICASSP40776.2020.9054312 [2020] :
- Performance bound for blind extraction of non-Gaussian complex-valued vector component from Gaussian background, 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2019, p. 5287-5291 Download DOI: 10.1109/ICASSP.2019.8683885 [2019] :
- Analýza korozního poškození potrubí s proudící párou pomocí akustické emise: výsledky pro potrubí 6. odběru v EBO, ÚTIA AVČR (Praha, 2018) [2018] :
- Detekce slabých signálů v šumu, UTIA AVČR (Praha, 2018) [2018] :
- Representations of Bayesian Networks by Low-Rank Models, Proceedings of Machine Learning Research, p. 463-472, Eds: Kratochvíl Václav, Studený Milan Download [2018] :
- Orthogonally-Constrained Extraction of Independent Non-Gaussian Component from Non-Gaussian Background Without ICA, Latent Variable Analysis and Signal Separation, p. 161-170, Eds: Deville Yannick, Gannot Sharon, Mason Russell, Plumbley Mark D., Ward Dominic Download DOI: 10.1007/978-3-319-93764-9_16 [2018] :
- Analýza korozního poškození potrubí s proudící párou pomocí akustické emise:\nteoretická východiska a první výsledky, ÚTIA AV ČR (Praha, 2017) Download [2017] :
- Odhad rychlosti šíření akustických vln ve vzorku oceli pro sledování creepových změn pomocí akustické emise, ÚTIA AV ČR (Praha, 2017) Download [2017] :
- Sledování creepových změn na tepelně a mechanicky namáhaném vzorku oceli pomocí akustické emise II, ÚTIA AV ČR (Praha, 2017) Download [2017] :
- Sledování creepových změn na tepelně a mechanicky namáhaném vzorku oceli pomocí akustické emise, UTIA AV ČR (Praha, 2017) Download [2017] :
- Under-Determined Tensor Diagonalization for Decomposition of Difficult Tensors, IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP) 2017 , p. 263-266 Download DOI: 10.1109/CAMSAP.2017.8313082 [2017] :
- Cramer-Rao-Induced Bound for Interference-to-Signal Ratio Achievable through Non-Gaussian Independent Component Extraction, IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP) 2017 , p. 94-97 Download DOI: 10.1109/CAMSAP.2017.8313097 [2017] :
- Orthogonally constrained independent component extraction: Blind MPDR beamforming, Proceedings of the 25th European Signal Processing Conference (EUSIPCO 2017), p. 1195-1199 Download DOI: 10.23919/EUSIPCO.2017.8081389 [2017] :
- Adaptive Blind Separation of Instantaneous Linear Mixtures of Independent Sources, Latent Variable Analysis and Signal Separation, 13th International Conference, LVA/ICA 2017, p. 172-181, Eds: Tichavský Petr, Babaie-Zadeh Massoud, Michel Olivier J.J., Thirion-Moreau Nadege Download DOI: 10.1007/978-3-319-53547-0 [2017] :
- Blind Source Separation of Single Channel Mixture Using Tensorization and Tensor Diagonalization, Latent Variable Analysis and Signal Separation, 13th International Conference, LVA/ICA 2017, p. 36-46, Eds: Tichavský Petr, Babaie-Zadeh Massoud, Michel Olivier J.J., Thirion-Moreau Nadege Download DOI: 10.1007/978-3-319-53547-0 [2017] :
- Partitioned Hierarchical Alternating Least Squares Algorithm for CP Tensor Decomposition, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2017, p. 2542-2546 Download DOI: 10.13140/RG.2.2.29610.82882 [2017] :
- Adaptive Blind Separation of Instantaneous Linear Mixtures of Independent Sources, ÚTIA AV ČR v.v.i (Praha, 2016) Download [2016] :
- Extension of the semi-algebraic framework for approximate CP decompositions via non-symmetric simultaneous matrix diagonalization, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Proocessing, p. 2971-2975 Download DOI: 10.1109/ICASSP.2016.7472222 [2016] :
- Rank-one tensor injection: A novel method for canonical polyadic tensor decomposition, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Proocessing, p. 2549-2553 Download DOI: 10.1109/ICASSP.2016.7472137 [2016] :
- Blind separation of underdetermined linear mixtures based on source nonstationarity and AR(1) modeling, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Proocessing, p. 4323-4327 Download DOI: 10.1109/ICASSP.2016.7472493 [2016] :
- Improving Relative Transfer Function Estimates Using Second-Order Cone Programming, Latent Variable Analysis and Signal Separation, p. 227-234, Eds: Vincent Emmanuel, Yeredor Arie, Koldovský Zbyněk, Tichavský Petr Download DOI: 10.1007/978-3-319-22482-4_4 [2015] :
- Rank Splitting for CANDECOMP/PARAFAC, Latent Variable Analysis and Signal Separation, p. 31-40, Eds: Vincent Emmanuel, Yeredor Arie, Koldovský Zbyněk, Tichavský Petr Download DOI: 10.1007/978-3-319-22482-4_4 [2015] :
- Blind Separation of Mixtures of Piecewise AR(1) Processes and Model Mismatch, Latent Variable Analysis and Signal Separation, p. 304-311, Eds: Vincent Emmanuel, Yeredor Arie, Koldovský Zbyněk, Tichavský Petr Download DOI: 10.1007/978-3-319-22482-4_35 [2015] :
- Two-sided diagonalization of order-three tensors, Proceedings of the 23rd European Signal Processing Conference (EUSIPCO 2015), p. 998-1002 Download DOI: 10.1109/EUSIPCO.2015.7362532 [2015] :
- Low rank tensor deconvolution, Proceedings of 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), p. 2169-2173 Download DOI: 10.1109/ICASSP.2015.7178355 [2015] :
- On semi-blind estimation of echo paths during double-talk based on nonstationarity, 2014 14th International Workshop on Acoustic Signal Enhancement (IWAENC), p. 198-202 Download DOI: 10.1109/IWAENC.2014.6954006 [2014] :
- Způsob potlačení šumu a zvýraznění řečového signálu pro mobilní telefon se dvěma nebo více mikrofony (2014) Download [2014] :
- An Approximate Tensor-Based Inference Method Applied to the Game of Minesweeper, Probabilistic Graphical Models, p. 535-550, Eds: van der Gaag Linda C. , Feelders Ad J. Download DOI: 10.1007/978-3-319-11433-0_35 [2014] :
- Vědecká spolupráce s japonskými ústavy, Středisko společných činností AV ČR, v. v. i (Praha, 2014) [2014] :
- On Fast Algorithms for Orthogonal Tucker Decomposition, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), p. 6766-6770 Download DOI: 10.1109/ICASSP.2014.6854910 [2014] :
- Deflation Method for CANDECOMP/PARAFAC Tensor Decomposition, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), p. 6736-6740 Download DOI: 10.1109/ICASSP.2014.6854904 [2014] :
- A Homotopy Recursive-in-Model-Order Algorithm for Weighted LASSO, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), p. 4179-4183 Download [2014] :
- Probabilistic Inference in BN2T Models by Weighted Model Counting, Proceedings of the Twelfth Scandinavian Conference on Artificial Intelligence, p. 275-284, Eds: Jaeger Manfred, Nielsen Thomas Dyhre, Viappiani Paolo Download DOI: 10.3233/978-1-61499-330-8-275 [2013] :
- Informed generalized sidelobe canceler utilizing sparsity of speech signals, Proceedings of MLSP2013 Download [2013] :
- Noise Reduction in Dual-Microphone Mobile Phones Using a Bank of Pre-Measured Target-Cancellation Filters, 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2013, p. 679-683 Download [2013] :
- A Further Improvement of a Fast Damped Gauss–Newton Algorithm for CANDECOMP-PARAFAC Tensor Decomposition, 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2013, p. 5964-5968 Download DOI: 10.1109/ICASSP.2013.6638809 [2013] :
- Tensor Completion Through Multiple Kronecker Product Decomposition, 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2013, p. 3233-3237 Download [2013] :
- From Basis Components to Complex Structural Patterns, 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing ICASSP 2013, p. 3228-3232 Download [2013] :
- Computationally efficient probabilistic inference with noisy threshold models based on a CP tensor decomposition, Proceedings of The Sixth European Workshop on Probabilistic Graphical Models, p. 355-362 Download [2012] :
- A treatment of EEG data by underdetermined blind source separation for motor imagery classification, 20th European Signal Processing Conference (EUSIPCO 2012), p. 1484-1488 Download [2012] :
- Algorithms for nonorthogonal approximate joint block-diagonalization, 20th European Signal Processing Conference (EUSIPCO 2012), p. 2094-2098 Download [2012] :
- Způsob slepé separace akustických signálů z jejich konvolutorní směsi (2012) Download [2012] :
- Low-rank blind nonnegative matrix deconvolution, IEEE International Conference on Acoustics, Speech, and Signal Processing 2012, p. 1893-1896 Download DOI: 10.1109/ICASSP.2012.6288273 [2012] :
- On Computation of Approximate Joint Block-Diagonalization Using Ordinary AJD, Latent Variable Analysis and Signal Separation, p. 163-171 Download DOI: 10.1007/978-3-642-28551-6_21 [2012] :
- Semi-blind Source Separation Based on ICA and Overlapped Speech Detection, Latent Variable Analysis and Signal Separation, p. 462-469 Download DOI: 10.1007/978-3-642-28551-6_57 [2012] :
- On Revealing Replicating Structures in Multiway Data: A Novel Tensor Decomposition Approach, Latent Variable Analysis and Signal Separation, p. 297-305 Download DOI: 10.1007/978-3-642-28551-6_37 [2012] :
- On Connection between the Convolutive and Ordinary Nonnegative Matrix Factorizations, Latent Variable Analysis and Signal Separation, p. 288-296 Download DOI: 10.1007/978-3-642-28551-6_36 [2012] :
- Experimental Comparison of Sparse Signal Recovery Algorithms, ÚTIA AVČR (Praha, 2011) Download [2011] :
- Damped Gauss-Newton algorithm for nonnegative Tucker Decomposition, 2011 IEEE Statistical Signal Processing Workshop (SSP) Proceedings, p. 669-672 Download [2011] :
- Stability Analysis and Fast Damped-Gauss-Newton Algorithm for INDSCALTensor Decomposition, 2011 IEEE Statistical Signal Processing Workshop (SSP) Proceedings, p. 581-584 Download [2011] :
- Blind Speech Separation in Time-Domain Using Block-Toeplitz Structure of Reconstructed Signal Matrices, Proceedings of the 12th Annual Conference of the International Speech Communication Association (Interspeech 2011), p. 561-564 Download [2011] :
- Fast damped Gauss-Newton algorithm for sparse and nonnegative tensor factorization, Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing 2011, p. 1988-1991 Download [2011] :
- Stability of CANDECOMP-PARAFAC tensor decomposition, Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing 2011, p. 4164-4167 Download DOI: 10.1109/ICASSP.2011.5947270 [2011] :
- Automatic Removal of Sparse Artifacts in Electroencephalogram, Proceedings of the Third International Conference on Bio-Inspired Systems and Signal Processing, Biosignals 2011, p. 530-535 Download DOI: 10.5220/0003276505300535 [2011] :
- Automatic Removal of Sparse Artifacts in Electroencephalogram, ÚTIA AV ČR (Praha, 2010) Download [2010] :
- Time-domain Blind Audio Source Separation Method Producing Separating Filters of Generalized Feedforward Structure, Lecture Notes in Computer Science, p. 17-24, Eds: Gavrilova M.L., Kumar V., Mun Y., Tan C.J.K., Gervasi O. Download [2010] :
- Subband Blind Audio Source Separation Using a Time-Domain Algorithm and Tree-Structured QMF Filter Bank, Lecture Notes in Computer Science, p. 25-32, Eds: Gavrilova M.L., Kumar V., Mun Y., Tan C.J.K., Gervasi O. Download [2010] :
- Adaptive Time-Domain Blind Separation of Speech Signals, Lecture Notes in Computer Science, p. 9-16, Eds: Gavrilova M.L., Kumar V., Mun Y., Tan C.J.K., Gervasi O. Download [2010] :
- Simultanous search for all modes in multilinear models, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing 2010, p. 4114-4117 Download [2010] :
- A Comparison of Independent Component and Independent Subspace Analysis Algorithms, 17th European Signal Processing Conference (EUSIPCO 2009), p. 1447-1451 Download [2009] :
- Odstraňování artefaktů v EEG datech III, ÚTIA AV ČR ( Praha, 2009) Download [2009] :
- On the Estimation of Mutual Information, ROBUST 2008, p. 263-269, Eds: Antoch J., Dohnal G. Download [2009] :
- A Fast Asymptotically Efficient Algorithm for Blind Separation of a Linear Mixture of Block-Wise Stationary Autoregressive Processes, Proceedings of 34th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), p. 3133-3136 Download [2009] :
- Time-domain Blind Audio Source Separation Using Advanced Component Clustering and Reconstruction, 2008 Hands-free Speech Communication and Microphone Arrays, p. 216-219 [2008] :
- Extension of EFICA Algorithm for Blind Separation of Piecewise Stationary Non-Gaussian Sources, ICASSP 2008: IEEE International Conference on Acoustics, Speech, and Signal Processing, p. 1913-1916 [2008] :
- A Fast Approximate Joint Diagonalization Algorithm Using a Criterion with a Block Diagonal Weight Matrix, ICASSP 2008: IEEE International Conference on Acoustics, Speech, and Signal Processing, p. 3321-3324 [2008] :
- Performance Analysis of Extended EFICA Algorithm, ÚTIA AV ČR (Praha, 2007) Download [2007] :
- A fast algorithm for blind separation of non-Gaussian and time-correlated signals, Proccedings of the 15th European Signal Processing Conference. EUSIPCO 2007, p. 1731-1735 [2007] :
- Time-Domain Blind Audio Source Separation using Advanced ICA Methods, Proccedings of the 8th Annual Conference of the International Speech Communication Association. Interspeech 2007, p. 1-4 [2007] :
- Ddentification of neonatal EEG sleep stages by structural time profiles and independent component analysis, Proc. of the 3rd WACBE World Congress on Bioengineering 2007, p. 1-4 [2007] :
- Asymptotic Analysis of Bias of FastICA-based Algorithms in Presence of Additive Noise, ÚTIA AV ČR (Praha, 2007) [2007] :
- Odstraňování artefaktů v EEG datech II, ÚTIA AV ČR (Praha, 2006) [2006] :
- Asymtotic Analysis of Bias of FastICA-based Algorithms in Presence of Additive Noise, ÚTIA AV ČR (Praha, 2006) [2006] :
- Fast Implementation of Asymtotically Optimized SOBI (WASOBI) Algorithm for Blind Separation of 100+ AR Sources, ÚTIA AV ČR (Praha, 2006) [2006] :
- Blind signal separation by combining two ICA algorithms: HOS-based EFICA and time structure-based WASOBI, Proceedings of 14th European Signal Processing Conference. EUSIPCO 2006, p. 1-5 [2006] :
- A Computationally Affordable Implementation of An Asymptotically Optimal BSS Algorithm for AR Sources, Proceedings of 14th European Signal Processing Conference. EUSIPCO 2006, p. 1-5 [2006] :
- Cramér-Rao Lower Bound for Blind Separation of Stationary Parametric Gaussian Sources, ÚTIA AV ČR (Praha, 2006) [2006] :
- Identification of epileptic activity in electroencephalograms using four techniques of independent component analysis, Analysis of Biomedical Signals and Images. BIOSIGNAL 2006, p. 166-168, Eds: Jan J., Kozumplík J., Provazník I. [2006] :
- Methods of Fair Comparsion of Performance of Linear ICA Techniques in Presence of Additive Noise, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, p. 873-876 [2006] :
- Blind Signal Separation by Combining Two ICA Algorythms: HOS-based EFICA and Time Structure-Based WASOBI, ÚTIA AV ČR (Praha, 2006) [2006] :
- Odstraňování artefaktů v EEG datech, ÚTIA AV ČR (Praha, 2005) [2005] :
- Efficient Variant of Algorithm FastICA for Independent Component Analysis Attaining the Cramér-Rao Lower Bound, ÚTIA AV ČR (Praha, 2005) [2005] :
- Efficient Variant of Algorithm FastICA for Independent Component Analysis Attaining the Cramér-Rao Lower Bound, ÚTIA AV ČR (Praha, 2005) [2005] :
- Performance Analysis of the FastICA Algorithm and Cramé-Rao Bounds for Linear Independent Component Analysis, ÚTIA AV ČR (Praha, 2005) [2005] :
- Asymptotic Performance of the FastICA Algorithm for Independent Component Analysis and its Iprovements, ÚTIA AV ČR (Praha, 2005) [2005] :
- Asymptotic performance of the FastICA algorithm for independent component analysis and its iprovements, Proceedings of the IEEE/SP 13th workshop on Statistical Signal Processing, p. 1-6 [2005] :
- Eficient variant of algorithm FastICA for independent component analysis attaining the Cramér-Rao lower bound, Proceedings of IEEE/SP 13th Workshop on Statistical Signal Processing, p. 7-12, Telecom Paris (Paris, 2005) [2005] :
- Cramer-Rao lower bound for linear independent component analysis, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, p. 581-584, IEEE (Philadelphia, 2005) [2005] :
- Methods of Fair Comparsion of Performance of Linear ICA Techniques in Presence of Additive Noise, ÚTIA AV ČR (Praha, 2005) [2005] :
- Computationally Feasible Implementation of Asymptotically Optimal Blind Separation Algorithm SOBI (WASOBI) for AR Source, ÚTIA AV ČR (Praha, 2005) [2005] :
- Cramér-Rao Lower Bound for Independent Component Analysis, ÚTIA AV ČR (Praha, 2004) [2004] :
- A reduced-complexity "blind" space-frequency algorithm for peer-to-peer MFSK-FFH-CDMA detection & co-channel interference suppression, IEEE Global Telecommunications Conference, p. 1-5, IEEE Communications Society (San Francisco, 2003) [2003] :
- Finite-data-record performance/breakdown analysis of the "Blind" space-time DS-CDMA rake-receiver of Wong-Lok-Lehnert-Zoltowski, Proceedings of the 2003 IEEE International Conference on Communications, p. 1-5, IEEE (Piscataway, 2003) [2003] :
- New fluid-mechanics-based statistical models of a nominally linear towed-array's shape deformation, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, p. 2841-2844, IEEE (Orlando, 2002) [2002] :
- Estimation and smoothing of instantaneous frequency of noisy narrow band signals, Signal Processing. Proceedings, p. 1803-1806, Eds: Gabbouj M., Kuosmanen P., TTKK (Tampere, 2000) [2000] :
- Independent component analysis through direct estimation of the mutual information, Independent Component Analysis and Blind Signal Separation. Proceedings, p. 69-74, Eds: Pajunen P., Karhunen J., IEEE Signal Processing Society (Helsinki, 2000) [2000] :
- Predictive and filtering lower bounds for nonlinear filters, IFAC World Congress 1999. Proceedings, p. 43-48, Pergamon (Oxford, 1999) [1999] :
- Cross-product algorithms for source tracking using an EM vector sensor, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, p. 2781-2784, IEEE (Phoenix, 1999) [1999] :
- Measuring performances of nonlinear filtering techniques, Proceedings of the 3rd Japan-Central Europe Joint Workshop on Modelling and Simulation of Non-linear Engineering Systems and Related Phenomena, p. 327-330, Eds: Mahel' M., Uesaka M., Ušák E., Comenius University (Bratislava, 1999) [1999] :
- Few General Remarks to Asymptotic Analyses, ÚTIA AV ČR (Praha, 1999) [1999] :
- Estimating parameters of polynomial phase signals by tracking algorithms, Proceedings of the 9th IEEE Signal Processing Workshop on Statistical Signal and Array Processing, p. 348-351, IEEE (Piscataway, 1998) [1998] :
- Multicomponent Polynomial Phase Signal Analysis Using a Tracking Algorithm, Royal Institute of Technology (Stockholm, 1998) [1998] :
- Performance analysis of a constrained high order adaptive notch filter, Proceedings of the 1997 Finnish Signal Processing Symposium, p. 21-24, TTKK (Pori, 1997) [1997] :
- Recursive estimation of linearly or harmonically modulated frequencies of multiple cisoids in noise, International Conference on Acoustics, Speech, and Signal Processing, p. 1925-1928, ICASSP Committee (München, 1997) [1997] :
- Posterior C-R bounds for performance of adaptive parameter estimation, Proceedings of the First European Conference on Signal Analysis and Prediction, p. 153-156, Eds: Procházka A., Uhlíř J., Sovka P., ICT Press (Prague, 1997) [1997] :
- Extension of a hyperstable adaptive line enhancer for tracking of multiple cisoids, Signal Processing VIII: Theories and Applications, p. 1271-1274, Eds: Sicuranza S. L., Ramponi G., EA Signal Processing (Trieste, 1996) [1996] :
- Matching of fourth order sample moments for frequency rate estimation, NORSIG '96. Proceedings, p. 311-314, TKK OFFSET (Espoo, 1996) [1996] :
- Comparative Study of Four Adaptive Frequency Trackers - Revised, ÚTIA AV ČR (Praha, 1996) [1996] :
- Frequency rate estimation based on fourth order sample moments, IEEE Signal Processing Workshop on Statistical Signal and Array Processing. Proceedings, p. 391-394, IEEE (Los Alamitos, 1996) [1996] :
- The n-th order moment (cumulant) of multiple sinusoids: strong ergodicity and related issues, Proceedings of the IEEE Signal Processing - Athos Workshop on High-Order Statistics, p. 337-342, IEEE (Girona, 1995) [1995] :
- Comparative Study of Four Adaptive Frequency Trackers, ÚTIA AV ČR (Praha, 1995) [1995] :
- Performance analysis of two algorithms for tracking of multiple noisy cisoids, Signal Processing, p. 1720-1723, Eds: Holt H., Cowan C., Grant P., Sandham W., European Association for Signal Processing (Edinburgh, 1994) [1994] :
- Aposteriori Cramer-Rao Bounds for Adaptive Harmonic Retrieval, ÚTIA AV ČR (Praha, 1994) [1994] :
- Two Algorithms for Adaptive Retrieval of Slowly Time-Varying Multiple Cisoids in Noise, ÚTIA AV ČR (Praha, 1994) [1994] :
- Statistical Characterization of Sample Fourth-Order Cumulants of a Noisy Complex Sinusoidal Process, ÚTIA AV ČR (Praha, 1994) [1994] :
- Two Algorithms for Adaptive Retrieval of Slowly Time-Varying Multiple Cisoids in Noise, Uppsala University (Uppsala, 1993) [1993] :
- Efficient Tracking of Multiple Sinusoids with Slowly Varying Parameters, IEEE Internatinal Conference on Acoustics, Speech and Signal Processing, p. 368-371, IEEE (New York, 1993) [1993] :
- On Consistency of Cumulant-Based Methods in the Harmonic Retrieval, ÚTIA AV ČR (Praha, 1993) [1993] :
- Large Sample Asymptotics for Signal-Subspace Methods in Sinusoidal Frequency Estimation, ÚTIA AV ČR (Praha, 1993) [1993] :
- Adaptive Filtering for Periodic Signal Enhancement and Tracking, Uppsala University (Uppsala, 1993) [1993] :
- Signal-Subspace Methods in Sinusoidal Frequency Estimation. CSc.Dissertation, ÚTIA ČSAV (Praha, 1992) [1992] :
- Efficient Tracking of Multiple Sinusoids with Slowly Varying Parameters, Uppsala University (Uppsala, 1992) [1992] :
- Odhad skrytých periodicit metodami autoregresního modelování, Sborník prací zimní školy JČSMF ROBUST 90, p. 152-154, JČMF (Praha, 1990) [1990] :
- Programový systém KECAL pro odhad skrytých periodicit - popis algoritmů a jejich použití, ÚTIA ČSAV (Praha, 1989) [1989] :
- Odhad spektrálních charakteristik a tvorba modelů nestacionárních signálů, ÚTIA ČSAV (Praha, 1989) [1989] :
- Odhad skrytých periodicit, ÚTIA ČSAV (Praha, 1989) [1989] :