Functional link based architectures for nonlinear acoustic echo cancellation

This paper introduces a collaborative architecture for nonlinear acoustic echo cancellation. This system is achieved linearly combining a standard linear filter and a functional link (FL) nonlinear filter. The FL filter is composed of merely nonlinear elements thus acting like a pure nonlinear kernel and modeling at best a nonlinear path. A more robust architecture is further introduced in which the FL filter is adaptively combined with an all-zero kernel (AZK) avoiding any gradient noise when nonlinearities are negligible. Experimental results show that proposed architectures present improved performance compared with other nonlinear echo cancellers notwithstanding the nonlinearity level in the echo path.

[1]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[2]  Rafik Goubran,et al.  Limitations of handsfree acoustic echo cancellers due to nonlinear loudspeaker distortion and enclosure vibration effects , 1995, Proceedings of 1995 Workshop on Applications of Signal Processing to Audio and Accoustics.

[3]  Rudolf Rabenstein,et al.  Nonlinear acoustic echo cancellation with 2nd order adaptive Volterra filters , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[4]  Raffaele Parisi,et al.  Acoustic echo cancellation in the presence of distorting loudspeakers , 2002, 2002 11th European Signal Processing Conference.

[5]  Udo Zoelzer,et al.  DAFX: Digital Audio Effects , 2011 .

[6]  Ali H. Sayed,et al.  Mean-square performance of a convex combination of two adaptive filters , 2006, IEEE Transactions on Signal Processing.

[7]  D. Mandic,et al.  SIGNAL MODALITY CHARACTERISATION USING COLLABORATIVE ADAPTIVE FILTERS , 2008 .

[8]  Magno T. M. Silva,et al.  Improving the Tracking Capability of Adaptive Filters via Convex Combination , 2008, IEEE Transactions on Signal Processing.

[9]  Aníbal R. Figueiras-Vidal,et al.  Adaptive Combination of Proportionate Filters for Sparse Echo Cancellation , 2009, IEEE Transactions on Audio, Speech, and Language Processing.

[10]  Jiashu Zhang,et al.  Adaptively Combined FIR and Functional Link Artificial Neural Network Equalizer for Nonlinear Communication Channel , 2009, IEEE Transactions on Neural Networks.

[11]  Danilo Comminiello,et al.  A Functional Link Based Nonlinear Echo Canceller Exploiting Sparsity , 2010 .

[12]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[13]  Xavier Serra,et al.  Digital Audio Effects , 2011 .

[14]  Aníbal R. Figueiras-Vidal,et al.  Adaptive Combination of Volterra Kernels and Its Application to Nonlinear Acoustic Echo Cancellation , 2011, IEEE Transactions on Audio, Speech, and Language Processing.