Conference Program – ICA 2009

Lecture Session I – Convolutive Mixtures

Session Chairs: Emmanuel Vincent (IRISA-INRIA, France) and Paris Smaragdis (Adobe Systems, USA)

• Modeling the Short Time Fourier Transform Ratio and Application to Underdetermined Audio Source Separation
  Dinh-Tuan Pham, Zaher El-Chami, Alexandre Guérin, and Christine Servière


• Blind Order Detection and Parameter Estimation of MISO-FIR Channels
  Carlos Estevão Fernandes, Pierre Comon, and Gérard Favier


• Adapted Deflation Approach for Referenced Contrast Optimization in Blind MIMO Convolutive Source Separation
  Rémi Dubroca, Christophe De Luigi, and Eric Moreau


• A Method for Filter Shaping in Convolutive Blind Source Separation
  Radoslaw Mazur and Alfred Mertins


• Online Subband Blind Source Separation For Convolutive Mixtures Using A Uniform Filter Bank With Critical Sampling
  Paulo B. Batalheiro, Mariane R. Petraglia, and Diego B. Haddad

Poster Session I – Theory, Convolutive Mixtures and Communications

Session Chair: Charles Casimiro Cavalcante (UFC, Brazil)

• Blind Separation of Cyclostationary Signals
  Nhat Anh Cheviet, Mohamed El Badaoui, Adel Belouchrani, and François Guillet


• Cebysev Coefficients-Based Algorithm for Estimating the ICA Model
  Doru Constantin


• Histogram Based Blind Identification and Source Separation from Linear Instantaneous Mixtures
  Konstantinos I. Diamantaras and Theophilos Papadimitriou


• Blind Source Separation of Post-Nonlinear Mixtures Using Evolutionary Computation and Gaussianization
  Tiago M. Dias, Romis Attux, João M. T. Romano, and Ricardo Suyama


• On IIR Filters and Convergence Acceleration For Convolutive Blind Source Separation
  Diego B. Haddad, Mariane R. Petraglia, and Paulo B. Batalheiro


• Time Frequency Masking Strategy for Blind Source Separation of Acoustic Signals Based on Optimally-Modified LOG-Spectral Amplitude Estimator
  Eugen Hoffmann, Dorothea Kolossa, and Reinhold Orglmeister


• Comparison of Two Main Approaches to Joint SVD
  Gen Hori


• Solving the Acoustic Echo Cancellation Problem in Double-Talk Scenario Using Non-Gaussianity of the Near-End Signal
  Intae Lee, Charles E. Kinney, Bowon Lee, and Antonius A. C. M. Kalker


• Bayesian Robust PCA for Incomplete Data
  Jaakko Luttinen, Alexander Ilin, and Juha Karhunen


• Independent Component Analysis (ICA) using Pearsonian Density Function
  Abhijit Mandal and Arnab Chakraborty


• Underdetermined BSS of MISO OSTBC Signals - Ali Mansour, Joe Youssef, and Koffi
  Clement Yao


• An Analysis of Unsupervised Signal Processing Methods in the Context of Correlated Sources
  Aline Neves, Cristina Wada, Ricardo Suyama, Romis Attux, and João M. T. Romano


• Probabilistic Formulation of Independent Vector Analysis using Complex Gaussian Scale Mixtures
  Jason Palmer, Scott Makeig, and Ken Kreutz-Delgado


• Blind Channel Identification in (2 x 1) Alamouti Coded Systems Based on Maximizing the Eigenvalue Spread of Cumulant Matrices
  Héctor Pérez-Iglesias, Daniel Iglesia, Adriana Dapena, and Vicente Zarzoso


• Least Square Joint Diagonalization of Matrices Under an Intrinsic Scale Constraint
  Dinh-Tuan Pham and Marco Congedo


• Blind Separation of Noisy Mixtures of Non-Stationary Sources Using Spectral Decorrelation
  Hicham Saylani, Shahram Hosseini, and Yannick Deville


• Audio Watermark Detection Using Undetermined ICA
  Jongwon Seok and Hafiz Malik


• Separation of Convolutive Mixtures with Hybrid Sources
  Christine Servière


• Fast Parallel Estimation of High Dimensional Information Theoretical Quantities with Low Dimensional Random Projection Ensembles
  Zoltán Szabó and András Lörincz


• Soft Dimension Reduction for ICA by Joint Diagonalization on the Stiefel Manifold
  Fabian J. Theis, Thomas P. Cason, and P.-A. Absil


• Theoretical Analysis and Comparison of Several Criteria on Linear Model Dimension Reduction
  Shikui Tu and Lei Xu


• Nonlinear Blind Source Deconvolution Using Recurrent Prediction-Error Filters and an Artificial Immune System
  Cristina Wada, Douglas M. Consolaro, Rafael Ferrari, Ricardo Suyama, Romis Attux, and Fernando J. Von Zuben


• ICA by Maximizing Non-Stability
  Baijie Wang, Ercan E. Kuruoglu, and Junying Zhang

Lecture Session II - Theory

Session Chairs: Tulay Adali (UMBC, USA) and Dinh-Tuan Pham (UJF - Grenoble INP, France)

• On Optimal Selection of Correlation Matrices for Matrix-Pencil-Based Separation
  Arie Yeredor


• Blind Non-Stationary Sources Separation by Sparsity in a Linear Instantaneous Mixture
  Bertrand Rivet


• On the Relationships Between MMSE and Information-Theoretic-Based Blind Criterion for Minimum BER Filtering
  Charles C. Cavalcante and João M. T. Romano


• Estimating Squared-loss Mutual Information for Independent Component Analysis
  Taiji Suzuki and Masashi Sugiyama


• Minimum Determinant Constraint for Non-negative Matrix Factorization
  Reinhard Schachtner, Gerhard Pöppel, Ana Maria Tomé, and Elmar W. Lang

Lecture Session III: Semi-Blind Source Separation / Evaluation Session Paper

Session Chairs: Fabian Theis (Helmholtz Zentrum München, Germany) and Christian Jutten (INPG, France)

• Using Signal Invariants to Perform Nonlinear Blind Source Separation
  David N. Levin


• Reference Based Contrast Functions in a Semi-Blind Context
  Marc Castella and Eric Moreau


• ICA with Sparse Connections: Revisited
  Kun Zhang, Heng Peng, Laiwan Chan, and Aapo Hyvärinen


• Extension of Sparse, Adaptive Signal Decompositions to Semi-Blind Audio Source Separation
  Andrew Nesbit, Emmanuel Vincent, and Mark D. Plumbley


• The 2008 Signal Separation Evaluation Campaign: A Community-Based Approach to Large-Scale Evaluation
  Emmanuel Vincent, Shoko Araki, and Pau Bofill

Poster Session II – Special Session on Evaluation / Applications

Session Chair: Mariane Rembold Petraglia (UFRJ, Brazil)

Special Session on Evaluation

• Stereo Source Separation and Source Counting with MAP Estimation with Dirichlet Prior Considering Spatial Aliasing Problem
  Shoko Araki, Tomohiro Nakatani, Hiroshi Sawada, and Shoji Makino


• Blind Spectral-GMM Estimation for Underdetermined Instantaneous Audio Source Separation
  Simon Arberet, Alexey Ozerov, Rémi Gribonval, and Frédéric Bimbot


• Application of Two Time-Domain Convolutive Blind Source Separation Algorithms to the 2008 Signal Separation Evaluation Campaign (SiSEC) Data
  Scott Douglas


• Permutation Correction in Blind Source Separation Using Sliding Subband Likelihood Function
  Intae Lee


• Underdetermined Instantaneous Audio Source Separation via Local Gaussian Modeling
  Emmanuel Vincent, Simon Arberet, and Rémi Gribonval


• Principles and performance of the LI-TIFROM software
  Matthieu Puigt


• Blind source separation for convolutive mixtures by recursive ICA and permutation correction
  Francesco Nesta

Applications

• Segmentation of Natural and Man-Made Structures by Independent Component Analysis
  André Cavalcante, Fausto Lucena, Allan Kardec Barros, Yoshinori Takeuchi, and Noboru Ohnishi


• An Implementation of Floral Scent Recognition System using ICA combined with Correlation Coefficients
  Byeong-Geun Cheon, Yong-Wan Roh, Dong-Ju Kim, and Kwang-Seok Hong


• Topographic Independent Component Analysis Based on Fractal and Morphology Applied to Texture Segmentation
  Klaus Fabian Côco, Evandro Ottoni Teatini Salles, and Mario Sarcinelli Filho


• ICA-Based Method for Quantifying EEG Event Related Desynchronization
  Danton Ferreira, Antônio M. F. L. Miranda de Sá, Augusto Santiago Cerqueira, and José Manoel de Seixas


• Localization of Generalized Discharge Sources in Patients with Juvenile Myoclonic Epilepsy Using Independent Components Analysis
  Sidcley P. Gomes, Patrícia da Silva Sousa-Carvalho, Enio Aguiar, Anderson B. Silva, Fábio M. Braga, and Allan Kardec Barros


• Iterative Subspace Decomposition for Ocular Artifact Removal from EEG Recordings
  Cédric Gouy-Pailler, Reza Sameni, Marco Congedo, and Christian Jutten


• Denoising Single Trial Event Related Magnetoencephalographic Recordings
  Elina Karp, Lauri Parkkonen, and Ricardo Vigário


• Image Source Separation using Color Channel Dependencies
  Koray Kayabol, Ercan E. Kuruoglu, and Bulent Sankur


• Learning Natural Image Structure with a Horizontal Product Model
  Urs Köster, Jussi T. Lindgren, Michael Gutmann, and Aapo Hyvärinen


• Estimating Markov Random Field Potentials for Natural Images
  Urs Köster, Jussi T. Lindgren, and Aapo Hyvärinen


• Atrial Activity Extraction based on Statistical and Spectral Features
  Raul Llinares, Jorge Igual, Addisson Salazar, Julio Miró-Borrás, and Arturo Serrano


• ICA Mixture Modeling for the Classification of Materials in Impact-Echo Testing
  Addisson Salazar, Arturo Serrano, Raul Llinares, Luis Vergara, and Jorge Igual


• High-Energy Particles Online Discriminators Based on Nonlinear Independent Components
  Eduardo Simas Filho, José Manoel de Seixas, and Luiz P. Calôba


• BSS-Based Feature Extraction for Skin Lesion Image Classification
  Hans Georg Stockmeier, Heidi Bäcker, Wolfgang Bäumler, and Elmar W. Lang


• Estimating Hidden Influences in Metabolic and Gene Regulatory Networks
  Fabian J. Theis and Florian Blöchl


• Blind Decomposition of Spectral Imaging Microscopy: A Study on Artificial and Real Test Data
  Fabian J. Theis, Richard Neher, and Andre Zeug


• Spike Detection and Sorting: Combining Algebraic Differentiations with ICA
  Zoran Tiganj and Mamadou Mboup


• Image Denoising Using Sparse Representation
  SeyyedMajid Valiollahzadeh, Hamed Firouzi, Massoud Babaie-Zadeh, and Christian Jutten


• Network Traffic Flow Separation and Control Through a Hybrid ICA-Fuzzy Adaptive Algorithm
  Flávio Henrique Teles Vieira, Lígia Maria Carvalho Sousa, George E. Bozinis, and Wesley F. de Miranda


• Arabica: Robust ICA in a Pipeline
  Jarkko Ylipaavalniemi and Jyri Soppela

Lecture Session IV: Applications

Session Chairs: Ricardo Vigario (HUT, Finland) and Shoko Araki (NTT, Japan)

• Validity of the Independence Assumption for the Separation of Instantaneous and Convolutive Mixtures of Speech and Music Sources
  Matthieu Puigt, Emmanuel Vincent, and Yannick Deville


• Bayesian Non-Negative Matrix Factorization
  Mikkel Schmidt, Lars Kai Hansen, and Ole Winther


• Ion-selective Electrode Array based on a Bayesian Nonlinear Source Separation Method
  Leonardo Tomazeli Duarte, Christian Jutten, and Saïd Moussaoui


• Eye Movement Quantification In Functional MRI Data By Spatial Independent Component Analysis
  Ingo R. Keck, Volker Fischer, Carlos G. Puntonet, and Elmar W. Lang


• Target Speech Enhancement in Presence of Jammer and Diffuse Background Noise
  Jani Even, Hiroshi Saruwatari, and Kiyohiro Shikano

Lecture Session V: Subspace Decompositions

Session Chair: Arie Yeredor (Tel-Aviv University, Israel)

• Optimal Performance of Second-Order Multidimensional ICA
  Dana Lahat, Jean-François Cardoso, and Hagit Messer


• Stationary Subspace Analysis
  Paul von Buenau, Frank C. Meinecke, and Klaus-Robert Müller


• A Novel Subspace Clustering Method for Dictionary Design
  B. Vikrham Gowreesunker and Ahmed H. Tewfik


• Non-Independent BSS: A Model for Evoked MEG Signals with Controllable Dependencies
  Florian Kohl, Gerd Wübbeler, Dorothea Kolossa, Clemens Elster, Markus Bär, and Reinhold Orglmeister


• Hierarchical Extraction of Independent Subspaces of Unknown Dimensions
  Peter Gruber, Harold W. Gutch, and Fabian J. Theis

Poster Session III – Algorithms (Nonnegative Decompositions / Time-Frequency, Subspace and Sparsity-Based Approaches)

Session Chair: Romis Attux (UNICAMP, Brazil)

• Source Separation of Phase-Locked Subspaces
  Miguel Almeida and Ricardo Vigário


• Nonnegative Network Component Analysis by Linear Programming for Gene Regulatory Network Reconstruction
  Chunqi Chang, Zhi Ding, and Yeung Sam Hung


• Constructing Time-Frequency Dictionaries for Source Separation via Time-Frequency Masking and Source Localisation
  Ruairi de Fréin, Scott T. Rickard, and Barak A. Pearlmutter


• A Robust and Precise Solution to Permutation Indeterminacy and Complex Scaling Ambiguity in BSS-based Blind MIMO-OFDM Receiver
  Mahdi Khosravy, Mohammad Reza Alsharif, Bin Guo, Hai Lin, and Katsumi Yamashita


• A Cascade System for Solving Permutation and Gain Problems in Frequency-Domain BSS
  Daniel Iglesia, Héctor Pérez-Iglesias, and Adriana Dapena


• Narrow-band Short-Time Frequency-Domain Blind Signal Separation of Passive Sonar Signals
  Natanael Nunes de Moura, José Manoel de Seixas, and Eduardo Simas Filho


• An ICA-Based Method for Blind Source Separation in Sparse Domains
  Everton Z. Nadalin, Ricardo Suyama, and Romis Attux


• Blind Source Separation of Sparse Overcomplete Mixtures and Application to Neural Recordings
  Michal Natora, Felix Franke, Matthias Munk, and Klaus Obermayer


• Cumulative State Coherence Transform for a Robust Two-Channel Multiple Source Localization
  Francesco Nesta, Piergiorgio Svaizer, and Maurizio Omologo


• Image Coding and Compression by Sparse 3D Discrete Cosine Transform
  Hamid Palangi, Aboozar Ghaffari, Massoud Babaie-Zadeh, and Christian Jutten


• Iterative-Shift Cluster-Based Time-Frequency BSS for Fractional-Time-Delay Mixtures
  Matthieu Puigt and Yannick Deville


• Blind Source Separation with Spatio-Spectral Sparsity Constraints - Application to Hyperspectral Data Analysis
  Yassir Moudden, Jerome Bobin, Jean-Luc Starck, and Jalal Fadili


• Limitations of the Spectrum Masking Technique for Blind Source Separation
  Gustavo Fernandes Rodrigues and Hani Camille Yehia


• Improvement of the Initialization of ICA Time-Frequency Algorithms for Speech Separation
  Auxiliadora Sarmiento, Sergio Cruces, and Iván Durán


• Binary Nonnegative Matrix Factorization Applied to Semi-Conductor Wafer Test Sets
  Reinhard Schachtner, Gerhard Pöppel, and Elmar W. Lang


• Probabilistic Factorization of Non-Negative Data with Entropic Co-occurrence Constraints
  Paris Smaragdis, Madhusudana Shashanka, Bhiksha Raj, and Gautham J. Mysore


• Blind Extraction of Chaotic Sources from Gaussian White Noise Based on a Measure of Determinism
  Diogo C. Soriano, Ricardo Suyama, and Romis Attux


• A Sparsity-Based Method to Solve Permutation Indeterminacy in Frequency-Domain Convolutive Blind Source Separation
  Prasad Sudhakar and Rémi Gribonval


• Canonical Dual Approach to Binary Factor Analysis
  Ke Sun, Shikui Tu, David Yang Gao, and Lei Xu


• Complete Blind Subspace Deconvolution
  Zoltán Szabó


• Estimating Phase Linearity in The Frequency-Domain ICA Demixing Matrix
  Keisuke Toyama and Mark D. Plumbley


• Factor Analysis as Data Matrix Decomposition: A New Approach for Quasi-Sphering in Noisy ICA
  Steffen Unkel and Nickolay T. Trendafilov


• Signal Subspace Separation based on the Divergence Measure of a set of Wavelets Coefficients
  Vincent Vigneron and Aurélien Hazan


• Mixtures of Gamma Priors for Non-Negative Matrix Factorization Based Speech Separation
  Tuomas Virtanen and Ali Taylan Cemgil