Blind Separation of Speech Mixtures Vaninirappuputhenpurayil Gopalan REJU School of Electrical and Electronic Engineering Nanyang Technological University.

Slides:



Advertisements
Similar presentations
Independent Component Analysis: The Fast ICA algorithm
Advertisements

Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Dimension reduction (2) Projection pursuit ICA NCA Partial Least Squares Blais. “The role of the environment in synaptic plasticity…..” (1998) Liao et.
Comparison of different MIMO-OFDM signal detectors for LTE
G. Valenzise *, L. Gerosa, M. Tagliasacchi *, F. Antonacci *, A. Sarti * IEEE Int. Conf. On Advanced Video and Signal-based Surveillance, 2007 * Dipartimento.
Blind Source Separation of Acoustic Signals Based on Multistage Independent Component Analysis Hiroshi SARUWATARI, Tsuyoki NISHIKAWA, and Kiyohiro SHIKANO.
REAL-TIME INDEPENDENT COMPONENT ANALYSIS IMPLEMENTATION AND APPLICATIONS By MARCOS DE AZAMBUJA TURQUETI FERMILAB May RTC 2010.
Independent Component Analysis (ICA)
0 Pattern Classification All materials in these slides were taken from Pattern Classification (2nd ed) by R. O. Duda, P. E. Hart and D. G. Stork, John.
Reduced Support Vector Machine
Prénom Nom Document Analysis: Data Analysis and Clustering Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
3/24/2006Lecture notes for Speech Communications Multi-channel speech enhancement Chunjian Li DICOM, Aalborg University.
Subband-based Independent Component Analysis Y. Qi, P.S. Krishnaprasad, and S.A. Shamma ECE Department University of Maryland, College Park.
ICA-based Blind and Group-Blind Multiuser Detection.
Independent Component Analysis (ICA) and Factor Analysis (FA)
Audio Source Separation And ICA by Mike Davies & Nikolaos Mitianoudis Digital Signal Processing Lab Queen Mary, University of London.
An Introduction to Independent Component Analysis (ICA) 吳育德 陽明大學放射醫學科學研究所 台北榮總整合性腦功能實驗室.
ICA Alphan Altinok. Outline  PCA  ICA  Foundation  Ambiguities  Algorithms  Examples  Papers.
Linear and Non-Linear ICA-BSS I C A  Independent Component Analysis B S S  Blind Source Separation Carlos G. Puntonet Dept.of Architecture.
1 Blind Separation of Audio Mixtures Using Direct Estimation of Delays Arie Yeredor Dept. of Elect. Eng. – Systems School of Electrical Engineering Tel-Aviv.
Normalised Least Mean-Square Adaptive Filtering
SINGLE CHANNEL SPEECH MUSIC SEPARATION USING NONNEGATIVE MATRIXFACTORIZATION AND SPECTRAL MASKS Jain-De,Lee Emad M. GraisHakan Erdogan 17 th International.
ERP DATA ACQUISITION & PREPROCESSING EEG Acquisition: 256 scalp sites; vertex recording reference (Geodesic Sensor Net)..01 Hz to 100 Hz analogue filter;
Introduction to Adaptive Digital Filters Algorithms
Multiresolution STFT for Analysis and Processing of Audio
1 ELEN 6820 Speech and Audio Processing Prof. D. Ellis Columbia University Midterm Presentation High Quality Music Metacompression Using Repeated- Segment.
Eigenstructure Methods for Noise Covariance Estimation Olawoye Oyeyele AICIP Group Presentation April 29th, 2003.
Independent Component Analysis on Images Instructor: Dr. Longin Jan Latecki Presented by: Bo Han.
Heart Sound Background Noise Removal Haim Appleboim Biomedical Seminar February 2007.
“A fast method for Underdetermined Sparse Component Analysis (SCA) based on Iterative Detection- Estimation (IDE)” Arash Ali-Amini 1 Massoud BABAIE-ZADEH.
1 UTILIZING CHANNEL CODING INFORMATION IN CIVA- BASED BLIND SEQUENCE DETECTORS Xiaohua(Edward) Li Department of Electrical and Computer Engineering State.
Independent Component Analysis Zhen Wei, Li Jin, Yuxue Jin Department of Statistics Stanford University An Introduction.
2010/12/11 Frequency Domain Blind Source Separation Based Noise Suppression to Hearing Aids (Part 1) Presenter: Cian-Bei Hong Advisor: Dr. Yeou-Jiunn Chen.
ECE 8443 – Pattern Recognition LECTURE 10: HETEROSCEDASTIC LINEAR DISCRIMINANT ANALYSIS AND INDEPENDENT COMPONENT ANALYSIS Objectives: Generalization of.
A note about gradient descent: Consider the function f(x)=(x-x 0 ) 2 Its derivative is: By gradient descent (If f(x) is more complex we usually cannot.
An Introduction to Blind Source Separation Kenny Hild Sept. 19, 2001.
Lecture 4: Statistics Review II Date: 9/5/02  Hypothesis tests: power  Estimation: likelihood, moment estimation, least square  Statistical properties.
2010/12/11 Frequency Domain Blind Source Separation Based Noise Suppression to Hearing Aids (Part 2) Presenter: Cian-Bei Hong Advisor: Dr. Yeou-Jiunn Chen.
1 MaxEnt CNRS, Paris, France, July 8-13, 2006 “A Minimax Entropy Method for Blind Separation of Dependent Components in Astrophysical Images” Cesar.
Full-rank Gaussian modeling of convolutive audio mixtures applied to source separation Ngoc Q. K. Duong, Supervisor: R. Gribonval and E. Vincent METISS.
Optimal Component Analysis Optimal Linear Representations of Images for Object Recognition X. Liu, A. Srivastava, and Kyle Gallivan, “Optimal linear representations.
Channel Independent Viterbi Algorithm (CIVA) for Blind Sequence Detection with Near MLSE Performance Xiaohua(Edward) Li State Univ. of New York at Binghamton.
NCAF Manchester July 2000 Graham Hesketh Information Engineering Group Rolls-Royce Strategic Research Centre.
A Study of Sparse Non-negative Matrix Factor 2-D Deconvolution Combined With Mask Application for Blind Source Separation of Frog Species 1 Reporter :
Review of Spectral Unmixing for Hyperspectral Imagery Lidan Miao Sept. 29, 2005.
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition LECTURE 12: Advanced Discriminant Analysis Objectives:
Mathematical Analysis of MaxEnt for Mixed Pixel Decomposition
Independent Component Analysis Independent Component Analysis.
Single Correlator Based UWB Receiver Implementation through Channel Shortening Equalizer By Syed Imtiaz Husain and Jinho Choi School of Electrical Engineering.
Introduction to Independent Component Analysis Math 285 project Fall 2015 Jingmei Lu Xixi Lu 12/10/2015.
An Introduction of Independent Component Analysis (ICA) Xiaoling Wang Jan. 28, 2003.
MINUET Musical Interference Unmixing Estimation Technique Scott Rickard, Conor Fearon Department of Electronic & Electrical Engineering University College.
Instructor: Mircea Nicolescu Lecture 7
Spatial Covariance Models For Under- Determined Reverberant Audio Source Separation N. Duong, E. Vincent and R. Gribonval METISS project team, IRISA/INRIA,
Siemens Corporate Research Rosca et al. – Generalized Sparse Mixing Model & BSS – ICASSP, Montreal 2004 Generalized Sparse Signal Mixing Model and Application.
Benedikt Loesch and Bin Yang University of Stuttgart Chair of System Theory and Signal Processing International Workshop on Acoustic Echo and Noise Control,
Dimension reduction (1) Overview PCA Factor Analysis Projection persuit ICA.
Approaches of Interest in Blind Source Separation of Speech
LECTURE 11: Advanced Discriminant Analysis
Machine Learning Independent Component Analysis Supervised Learning
Estimation Techniques for High Resolution and Multi-Dimensional Array Signal Processing EMS Group – Fh IIS and TU IL Electronic Measurements and Signal.
Tirza Routtenberg Dept. of ECE, Ben-Gurion University of the Negev
Outlier Processing via L1-Principal Subspaces
PCA vs ICA vs LDA.
LOCATION AND IDENTIFICATION OF DAMPING PARAMETERS
Uniform Linear Array based Spectrum Sensing from sub-Nyquist Samples
A Fast Fixed-Point Algorithm for Independent Component Analysis
Independent Factor Analysis
Emad M. Grais Hakan Erdogan
Combination of Feature and Channel Compensation (1/2)
Presentation transcript:

Blind Separation of Speech Mixtures Vaninirappuputhenpurayil Gopalan REJU School of Electrical and Electronic Engineering Nanyang Technological University Vaninirappuputhenpurayil Gopalan REJU School of Electrical and Electronic Engineering Nanyang Technological University 11:51 PM1

Introduction Blind Source Separation 11:51 PM Mixing process: Unmixing process: Convolutive 2 s1s1 s2s2

Introduction Convolutive Blind Source Separation Instantaneous Blind Source Separation 11:51 PM3

Introduction Convolutive Blind Source Separation Instantaneous Blind Source Separation In frequency domain: Difficult to separate Easy to separate 11:51 PM4

Introduction No. of sources < No. of sensor No. of sources = No. of sensor No. of sources > No. of sensor Overdetermined mixing Determined mixing Underdetermined mixing Difficult to separate Easy to separate 11:51 PM5

Approaches for BSS of Speech Signals Types of mixing Instantaneous mixingConvolutive mixing 11:51 PM6

Approaches for BSS of Speech Signals Instantaneous mixing Step 1:Selection of cost function Step 2:Minimization or maximization of the cost function 11:51 PM WH S1S1 S2S2 X2X2 Y1Y1 Y2Y2 Separated? X1X1 7

Approaches for BSS of Speech Signals Instantaneous mixing Selection of cost function Statistical independence Information theoretic Non-Gaussianity Kurtosis Negentropy Nonlinear cross moments Temporal structure of speech Non-stationarity of speech 11:51 PM Central limit theorem: Mixture of two or more sources will be more Gaussian than their individual components Non Gaussianity measures: Signals from two different sources are independent 8

Approaches for BSS of Speech Signals Instantaneous mixing Minimization or maximization of the cost function simple gradient method Natural gradient method Newton’s method e.g. Informax ICA algorithm e.g. FastICA 11:51 PM9

Approaches for BSS of Speech Signals Convolutive Mixing Time Domain: Frequency Domain: Advantage: No permutation problem Disadvantage: Slow convergence High computational cost for long filter taps Advantage: Low computational cost Fast convergence Disadvantage: Permutation Problem WH S1S1 S2S2 X1X1 X2X2 Y 1 Y 2 Y 2 Y 1 11:51 PM10 or

Permutation Problem in Frequency Domain BSS f1f1 f2f2 fkfk x1x1 x2x2 x3x3 BSS Mixed signals K point FFT y1y1 y2y2 y3y3 Still signals are mixed K point IFFT Corresponding to different sources Due to permutation problem One frequency bin Instantaneous ICA algorithm Solving permutation Problem y1y1 y2y2 y3y3 Separated signals Corresponding to y 3 11:51 PM11

Motivation 11:51 PM # mixtures ≥ # sources # mixtures < # sources BSS Determined/ Overdetermined Underdetermined Instantaneous Convolutive Frequency domain Time domain Mixing matrix estimation Frequency bin- wise separation Permutation problem Source estimation Automatic detection of no. of sources 12

My Contribution - I 11:51 PM # mixtures ≥ # sources # mixtures < # sources BSS Determined/ Overdetermined Underdetermined Instantaneous Convolutive Frequency domain Time domain Mixing matrix estimation Frequency bin- wise separation Permutation problem Source estimation Automatic detection of no. of sources 13

Algorithm for Solving the Permutation Problem f1f1 f2f2 fkfk x1x1 x2x2 x3x3 BSS Mixed signals K point FFT y1y1 y2y2 y3y3 Separated signals K point IFFT Solving permutation Problem Permutation problem One frequency bin Instantaneous ICA algorithm Permutation problem solved 11:51 PM14

Existing Method for Solving the Permutation Problem Direction Of Arrival (DOA) method: Position of the p th sensor Velocity of sound 11:51 PM Direction of y 1 = -30 o Direction of y 2 = 20 o 15

Existing Method for Solving the Permutation Problem Reasons for failure at lower freq:  Lower spacing causes error in phase difference measurement.  The relation is approximated for plane wave front under anechoic condition Disadvantages:  Fails at lower frequencies.  Fails when sources are near.  Room reverberation.  Sensor positions must be known. Direction Of Arrival (DOA) method: 11:51 PM16

Existing Method for Solving the Permutation Problem f1f1 f2f2 fkfk BSS Mixed signals K point FFT y1y1 y2y2 y3y3 Separated signals K point IFFT Solving permutation Problem Low correlation High correlation Low correlation x1x1 x2x2 x3x3 Adjacent bands correlation method: 11:51 PM17

K-1 K K+1K+2 K+3 …….. K-1 K K+1K+2 K+3 …….. r12 r21 r11 r22 r11 r12 r21 r12 r21 r12 r21 r11 r12 r21 r22 s1s1 s2s2 Correlation matrix No change Change permutation Existing Method for Solving the Permutation Problem Adjacent bands correlation method: 11:51 PM With confidenceWithout confidence Example 18

K-1 K K+1K+2 K+3 …….. K-1 K K+1K+2 K+3 …….. r12 r21 r11 r22 r11 r12 r21 r12 r21 r12 r21 r11 r12 r21 r22 s1s1 s2s2 Correlation matrix Disadvantage: The method is not robust Existing Method for Solving the Permutation Problem Adjacent bands correlation method: 11:51 PM19

11:51 PM Existing Method for Solving the Permutation Problem Combination of DOA and Correlation methods method: DOA + Harmonic Correlation + Adjacent bands correlation Advantage: Increased robustness 20

Proposed algorithm: Partial separation method (Parallel configuration) Reference: V. G. Reju, S. N. Koh and I. Y. Soon, “Partial separation method for solving permutation problem in frequency domain blind source separation of speech signals,” Neurocomputing, Vol. 71, NO. 10–12, June 2008, pp. 2098– :51 PM21 Time domain stage Frequency domain stage

Partial separation method (Parallel configuration) 11:51 PM22 Time domain stage Frequency domain stage

Parallel configuration Partial separation method (Cascade configuration) 11:51 PM23 Time domain stage Frequency domain stage

Advantages of Partial Separation method Robustness 11:51 PM24

Comparison with Adjacent Bands Correlation Method 11:51 PM25

PS - Partial Separation method with confidence check, C1 - Correlation between the adjacent bins without confidence check, C2 - Correlation between adjacent bins with confidence check, Ha - Correlation between the harmonic components with confidence check, PS1 - Partial separation method alone without confidence check. 11:51 PM26 Comparison with DOA method

My Contribution -II 11:51 PM # mixtures ≥ # sources # mixtures < # sources BSS Determined/ Overdetermined Underdetermined Instantaneous Convolutive Frequency domain Time domain Mixing matrix estimation Frequency bin- wise separation Permutation problem Source estimation Automatic detection of no. of sources 27

Underdetermined Blind Source Separation of Instantaneous Mixtures Mixture in time domain Time to TF domain Detection of SSPs Mixing matrix estimation Estimation of Sources 11:51 PM28

Mathematical Representation of Instantaneous Mixing Reference: V. G. Reju, S. N. Koh and I. Y. Soon, “An algorithm for mixing matrix estimation in instantaneous blind source separation,” Signal Processing, Vol. 89, Issue 9, September 2009, pp. 1762–1773. Time domain: Time-Frequency domain: 11:51 PM29 P – No. of mixtures Q – No. of sources

Single Source Points in Time-Frequency domain Single source point 1Single source point 2 11:51 PM

Single source point 1Single source point 2 Single Source Points in Time-Frequency domain 11:51 PM31

Single source point 1Single source point 2 Scalar.·. At single source point 1:.·. At single source point 2: Single Source Points in Time-Frequency domain 11:51 PM32

Scatter Diagram of the Mixtures When Source are Perfectly Sparse Example: 11:51 PM33

Example: Scatter Diagram of the Mixtures When Source are Not Perfectly Sparse 11:51 PM34

Scatter Diagram of the Mixtures when Sources are Sparse 11:51 PM No. of sources = 6 No. of mixtures = 2 35

Scatter Diagram of the Mixtures when Sources are Sparse, After Clustering 11:51 PM No. of sources = 6 No. of mixtures = 2 36

Scatter Diagram of the Mixtures when Sources are Not Perfectly Sparse 11:51 PM Objective: Estimation of the single source points. No. of sources = 6 No. of mixtures = 2 37

Principle of the Proposed Algorithm for the Detection of Single Source Points Single source point 1Single source point 2 Scalar 11:51 PM Multi source point 38

Single source point 1Single source point 2 Scalar 11:51 PM Principle of the Proposed Algorithm for the Detection of Single Source Points Multi source point 39

Average of 15 pairs of speech utterances of length 10 s each 11:51 PM Principle of the Proposed Algorithm for the Detection of Single Source Points SSP MSP 40

SSP MSP Proposed Algorithm for the Detection of Single Source Points 11:51 PM41

Elimination of Outliers SSPs detection Clustering Outlier elimination 11:51 PM42

11:51 PM Experimental Results No. of mixtures =2, No. of sources =6 43

Detected Single Source Points, Three mixtures No. of mixtures =3, No. of sources =6 11:51 PM44

Comparison with Classical Algorithms for Determined Case No. of mixtures =2 No. of sources =2 Average of 500 experimental results 11:51 PM45 ->

Comparison with Method Proposed in [1], Underdetermined case [1] Y. Li, S. Amari, A. Cichocki, D. W. C. Ho, and S. Xie, “Underdetermined blind source separation based on sparse representation,” IEEE Transactions on Signal Processing, vol. 54, p. 423–437, Feb :51 PM Normalized mean square error (NMSE) in mixing matrix estimation (dB) Order of the mixing matrices (PxQ) 46 P – No. of mixtures Q – No. of sources

Advantages of the Proposed algorithm Step 1: Convert x in the time domain to the TF domain to get X. Step 2: Check the condition Step 3: If the condition is satisfied, then X(k, t) is a sample at the SSP, and this sample is kept for mixing matrix estimation; otherwise, discard the point. Step 4: Repeat Steps 2 to 3 for all the points in the TF plane or until sufficient number of SSPs are obtained. 1) Much simpler constrain: the algorithm does not require “single source zone”. 3) The algorithm is extremely simple but effective 2) Separation performance is better. 11:51 PM47 ->

My Contributions – III, IV and V 11:51 PM # mixtures ≥ # sources # mixtures < # sources BSS Determined/ Overdetermined Underdetermined Instantaneous Convolutive Frequency domain Time domain Mixing matrix estimation Frequency bin- wise separation Permutation problem Source estimation Automatic detection of no. of sources 48

Underdetermined Convolutive Blind Source Separation via Time-Frequency Masking Reference: V. G. Reju, S. N. Koh and I. Y. Soon, “Underdetermined Convolutive Blind Source Separation via Time- Frequency Masking,” IEEE Transactions on Audio, Speech and Language Processing, Vol. 18, NO. 1, Jan. 2010, pp. 101–116. STFT Apply Mask Apply mask Mask estimation Mic 1 Mic P Mixture in TF domain Separated signals in TF domain 11:51 PM49

Mathematical Representation Time domain: Frequency domain: 11:51 PM50 P – No. of mixtures Q – No. of sources

Single source points Instantaneous mixing Single source point 1Single source point 2 Real scalar Real Real scalar Convolutive mixing Single source point 1Single source point 2 Complex scalar Complex Complex scalar 11:51 PM51

Basic Principle of Single Source Points Detection Convolutive mixing Single source point 1Single source point 2 Complex scalar Complex Complex scalar The Hermitian angle between the complex vectors u 1 and u 2 will remain the same even if the vectors are multiplied by any complex scalars, whereas the pseudo angle will change. 11:51 PM52 ->

Algorithm for Single Source Points Detection θH2θH2 θH1θH1 θH2θH2 11:51 PM53 θH1θH1 OR

Clean Estimated Mask Estimation by k-means (KM) 11:51 PM54

Clean Estimated Mask Estimation by Fuzzy c-means (FCM) 11:51 PM55

Automatic Detection of Number of Sources 11:51 PM56 Cluster validation technique: For c = 2 to c max Cluster the data into c clusters. Calculate the cluster validation index. End Take c corresponding to the best cluster as the number of sources. ->

Elimination of Low Energy Points 11:51 PM57