Single channel nonstationary stochastic signal separation using linear time-varying filters

Separability of signal mixtures given only one mixture observation is defined as the identification of the accuracy to which the signals can be separated. The paper shows that when signals are separated using the generalized Wiener filter, the degree of separability can be deduced from the signal structure. To identify this structure, the processes are represented on an general spectral domain, and a sufficient solution to the Wiener filter is obtained. The filter is composed of a term independent of the signal values, corresponding to regions in the spectral domain where the desired signal components are not distorted by interfering noise components, and a term dependent on the signal correlations, corresponding to the region where components overlap. An example of determining perfect separability of modulated random signals is given with application in radar and speech processing.

[1]  Paul R. White,et al.  THE ANALYSIS OF NON-STATIONARY SIGNALS USING TIME-FREQUENCY METHODS , 1996 .

[2]  Sidney Darlington,et al.  Nonstationary smoothing and prediction using network theory concepts , 1959, IRE Trans. Inf. Theory.

[3]  Leon Cohen,et al.  Generalization of the Wiener-Khinchin theorem , 1998, IEEE Signal Processing Letters.

[4]  William D. Mark.  Power spectral representation of nonstationary random processes defined over semi‐infinite intervals , 1976 .

[5]  William A. Gardner,et al.  Correlation estimation and time-series modeling for nonstationary processes , 1988 .

[6]  Khaled H. Hamed,et al.  Time-frequency analysis , 2003 .

[7]  Athanasios Papoulis,et al.  Probability, Random Variables and Stochastic Processes , 1965 .

[8]  R. H. Battin,et al.  Random Processes in Automatic Control. , 1957 .

[9]  Richard A. Silverman,et al.  Locally stationary random processes , 2018, IRE Trans. Inf. Theory.

[10]  Israel Gohberg,et al.  A frequency response function for linear, time-varying systems , 1995, Math. Control. Signals Syst..

[11]  L. Zadeh,et al.  Frequency Analysis of Variable Networks , 1950, Proceedings of the IRE.

[12]  Lotfi A. Zadeh,et al.  The Determination of the Impulsive Response of Variable Networks , 1950 .

[13]  Michael Unser,et al.  Splines: a perfect fit for signal and image processing , 1999, IEEE Signal Process. Mag..

[14]  Ananthram Swami,et al.  On estimating random amplitude chirp signals , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[15]  V.Z. Marmarelis.  A single-record estimator for correlation functions of nonstationary random processes , 1981, Proceedings of the IEEE.

[16]  Allen Gersho,et al.  Characterization of time-varying linear systems , 1963 .

[17]  C. Tamvaclis.  Filtration of separable finite discrete signals , 1981 .

[18]  M. Shinbrot,et al.  A generalization of a method for the solution of the integral equation arising in optimization of time-varying linear systems with nonstationary inputs , 1957, IRE Trans. Inf. Theory.

[19]  Dennis Gabor,et al.  Theory of communication , 1946 .

[20]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[21]  L. Cohen,et al.  Time-frequency distributions-a review , 1989, Proc. IEEE.

[22]  Gerald Matz,et al.  lutionary Spectral m of Nonstationary , 1997 .

[23]  O. Grace.  Instantaneous power spectra , 1981 .

[24]  Gary F. Margrave.  Theory of Nonstationary Linear Filtering In the Fourier Domain , 1997 .

[25]  I. Miller.  Probability, Random Variables, and Stochastic Processes , 1966 .

[26]  François N. Frenkiel,et al.  Correlations and spectra for non-stationary random functions , 1962 .

[27]  Lotfi A. Zadeh,et al.  On the theory of filtration of signals , 1952 .

[28]  F. Donati,et al.  Finite-time averaged power spectra , 1971, IEEE Trans. Inf. Theory.

[29]  Leon Cohen,et al.  A general approach for obtaining joint representations in signal analysis. I. Characteristic function operator method , 1996, IEEE Trans. Signal Process..

[30]  W. D. Mark.  Spectral analysis of the convolution and filtering of non-stationary stochastic processes , 1970 .

[31]  Richard H. Battin,et al.  Random Processes in Automatic Control. , 1957 .

[32]  P. Rayner,et al.  SINGLE CHANNEL SIGNAL SEPARATION USING LINEAR TIME VARYING FILTERS : SEPARABILITY OF NON-STATIONARY STOCHASTIC SIGNALS , 1998 .

[33]  Douglas L. Jones,et al.  Equivalence of generalized joint signal representations of arbitrary variables , 1996, IEEE Trans. Signal Process..

[34]  Dante C. Youla,et al.  The solution of a homogeneous Wiener-Hopf integral equation occurring in the expansion of second-order stationary random functions , 1957, IRE Trans. Inf. Theory.

[35]  Henry D'Angelo,et al.  Linear time-varying systems : analysis and synthesis , 1970 .

[36]  M. Shinbrot,et al.  On the Integral Equation Occurring in Optimization Theory with Nonstationary Inputs , 1957 .

[37]  Lotfi A. Zadeh,et al.  Solution of an integral equation occurring in the theories of prediction and detection , 1956, IRE Trans. Inf. Theory.

[38]  Z. Zalevsky,et al.  The Fractional Fourier Transform: with Applications in Optics and Signal Processing , 2001 .

[39]  J. Bendat,et al.  A General Theory of Linear Prediction and Filtering , 1956 .

[40]  Mounir Ghogho,et al.  Maximum likelihood estimation of amplitude-modulated time series , 1999, Signal Process..

[41]  M. B. Priestley,et al.  Non-linear and non-stationary time series analysis , 1990 .

[42]  A. El-Jaroudi,et al.  The generalized evolutionary spectrum , 1996, IEEE Trans. Signal Process..

[43]  James R. Hopgood.  Nonstationary signal processing with application to reverberation cancellation in acoustic environments , 2000 .

[44]  Lotfi A. Zadeh,et al.  A general theory of linear signal transmission systems , 1952 .

[45]  R. Loynes.  On the Concept of the Spectrum for Non‐Stationary Processes , 1968 .

[46]  Lotfi A. Zadeh,et al.  Generalized Ideal Filters , 1952 .

[47]  Olivier Besson,et al.  On estimating the frequency of a sinusoid in autoregressive multiplicative noise , 1993, Signal Process..

[48]  M. Amin.  Time-varying spectrum estimation for a general class of nonstationary processes , 1986, Proceedings of the IEEE.

[49]  C. Turner.  On the Concept of an Instantaneous Power Spectrum, and Its Relationship to the Autocorrelation Function , 1954 .

[50]  Vasilis Z. Marmarelis.  Practical estimation of correlation functions of nonstationary Gaussian processes , 1983, IEEE Trans. Inf. Theory.

[51]  L. Zadeh,et al.  Time-Varying Networks, I , 1961, Proceedings of the IRE.

[52]  Phillip A. Bello,et al.  Time-frequency duality , 1964, IEEE Trans. Inf. Theory.

[53]  Morris J. Levin,et al.  Instantaneous spectra and ambiguity functions (Corresp.) , 1964, IEEE Trans. Inf. Theory.

[54]  L. Zadeh,et al.  Correlation Functions and Power Spectra in Variable Networks , 1950, Proceedings of the IRE.

[55]  Boualem Boashash,et al.  Cross spectral analysis of nonstationary processes , 1990, IEEE Trans. Inf. Theory.

[56]  Peter J. W. Rayner,et al.  Single channel separation using linear time varying filters: separability of non-stationary stochastic signals , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[57]  D. Lampard.  Generalization of the Wiener‐Khintchine Theorem to Nonstationary Processes , 1954 .

[58]  Y. H. Tsao,et al.  Uncertainty principle in frequency–time methods , 1984 .

[59]  H. Cramér.  On Some Classes of Nonstationary Stochastic Processes , 1961 .