New Insights into Convergence Theory of Constrained Frequency-Domain Adaptive Filters

Two kinds of update equations are commonly used for the constrained frequency-domain adaptive filter (FDAF), namely the gradient-constrained version and the weight-constrained version. The constraint is imposed only on the stochastic gradient vector in the first version, while it is imposed on the whole weight vector in the second version. It was already found that the two versions have different convergence behaviors, but a rigors analysis of the convergence behavior of the gradient-constrained FDAF is still lacking so far. This paper presents a comprehensive statistical analysis of the gradient-constrained FDAF. We set up an equivalent update equation of the gradient-constrained FDAF, which provides a close link with that of the weight-constrained version. Then, the mean and mean-square convergence behaviors of the gradient-constrained FDAF are analyzed using the new update equation, and the corresponding steady-state solutions are provided. Theoretical results confirm that the gradient-constrained FDAF will converge to a biased solution and exhibits a larger mean-square error than the weight-constrained version when, for instance, the weight vector is not initialized properly. Simulation results agree with our theoretical predictions very well.

[1]  Yong Xu,et al.  Steady-State Solution of the Deficient Length Constrained FBLMS Algorithm , 2012, IEEE Transactions on Signal Processing.

[2]  Jun Yang,et al.  Frequency-Domain Filtered-x LMS Algorithms for Active Noise Control: A Review and New Insights , 2018, Applied Sciences.

[3]  Jacob Benesty,et al.  A Multidelay Double-Talk Detector Combined with the MDF Adaptive Filter , 2003, EURASIP J. Adv. Signal Process..

[4]  Jun Yang,et al.  A Computationally Efficient Delayless Frequency-Domain Adaptive Filter Algorithm , 2013, IEEE Transactions on Circuits and Systems II: Express Briefs.

[5]  José Manuel Páez-Borrallo,et al.  On the implementation of a partitioned block frequency domain adaptive filter (PBFDAF) for long acoustic echo cancellation , 1992, Signal Process..

[6]  Martin Schneider,et al.  The generalized frequency-domain adaptive filtering algorithm as an approximation of the block recursive least-squares algorithm , 2016, EURASIP J. Adv. Signal Process..

[7]  J. Shynk.  Frequency-domain and multirate adaptive filtering , 1992, IEEE Signal Processing Magazine.

[8]  M. N. Shanmukha Swamy,et al.  A New Hybrid Active Noise Control System with Convex Combination of Time and Frequency Domain Filtered-X LMS Algorithms , 2018, Circuits Syst. Signal Process..

[9]  Tim Fingscheidt,et al.  Improved Measurement Noise Covariance Estimation for N-channel Feedback Cancellation Based on the Frequency Domain Adaptive Kalman Filter , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Walter Kellermann,et al.  Significance-aware filtering for nonlinear acoustic echo cancellation , 2016, EURASIP J. Adv. Signal Process..

[11]  Xiaofei Wang,et al.  Robust Uncertainty Control of the Simplified Kalman Filter for Acoustic Echo Cancelation , 2016, Circuits Syst. Signal Process..

[12]  Sen M. Kuo,et al.  Active Noise Control Systems: Algorithms and DSP Implementations , 1996 .

[13]  Peter Vary,et al.  Frequency-domain adaptive Kalman filter for acoustic echo control in hands-free telephones , 2006, Signal Process..

[14]  Behrouz Farhang-Boroujeny,et al.  Analysis of the frequency-domain block LMS algorithm , 2000, IEEE Trans. Signal Process..

[15]  Paulo S. R. Diniz,et al.  Adaptive Filtering: Algorithms and Practical Implementation , 1997 .

[16]  Allen G. Lindgren,et al.  Analysis of partitioned frequency-domain LMS adaptive algorithm with application to a hands-free telephone system echo canceller , 2000 .

[17]  Sanjit K. Mitra,et al.  Block implementation of adaptive digital filters , 1981 .

[18]  T. Moon,et al.  Mathematical Methods and Algorithms for Signal Processing , 1999 .

[19]  E. Ferrara.  Fast implementations of LMS adaptive filters , 1980 .

[20]  P. Sommen,et al.  On frequency domain adaptive filters using the overlap-add method , 1988, 1988., IEEE International Symposium on Circuits and Systems.

[21]  Ali H. Sayed,et al.  Fundamentals Of Adaptive Filtering , 2003 .

[22]  S. Mitra,et al.  A unified approach to time- and frequency-domain realization of FIR adaptive digital filters , 1983 .

[23]  Arie Feuer.  Performance analysis of the block least mean square algorithm , 1985 .

[24]  A. Gray,et al.  Unconstrained frequency-domain adaptive filter , 1982 .

[25]  Kheong Sann Chan,et al.  Analysis of the partitioned frequency-domain block LMS (PFBLMS) algorithm , 2001, IEEE Trans. Signal Process..

[26]  Gerald Enzner,et al.  A Unified Approach to the Statistical Convergence Analysis of Frequency-Domain Adaptive Filters , 2019, IEEE Transactions on Signal Processing.

[27]  A. Janssen,et al.  Convergence analysis of a frequency-domain adaptive filter with exponential power averaging and generalized window function , 1987 .

[28]  B. Farhang-Boroujeny,et al.  Adaptive Filters: Theory and Applications , 1999 .

[29]  Chong Kwan Un,et al.  Performance analysis of frequency-domain block LMS adaptive digital filters , 1989 .

[30]  Mohamed-Slim Alouini,et al.  Instantly decodable network coding for real-time device-to-device communications , 2016, EURASIP J. Adv. Signal Process..

[31]  Roberto Cristi,et al.  On the Steady State Performance of Frequency Domain LMS Algorithms , 1993, IEEE Trans. Signal Process..