|
|
| Publication: A.N. Birkett and R.A. Goubran, "Acoustic Echo cancellation using NLMS-Neural Network Structures", IEEE International Conference on Acoustic Speech and Signal Processing, ICASSP 1995, Detroit Michigan, May 1995, Vol. 5, pp. 3035-3038. |
| Abstract: One of the limitations of linear adaptive echo cancellers is nonlinearitie s which are generated mainly in the loudspeaker. The nonlinearity in the loudspeaker produce distortion at low frequencies and at large output amplitudes. The complete acoustic channel can be modeled as a nonlinear system convolved with a linear dispersive echo channel. Two new acoustic echo canceller models are developed to improve nonlinear performance. The first model consists of a time-delay feedforward neural network (TDNN) and the second model consists of a memoryless neural network followed by an adaptive NLMS structure. Simulations demonstrate that both neural network based structures improve the Echo Return Loss Enhancement (ERLE) performance compared to a linear NLMS acoustic echo canceller. Experimental results using the TDNN improved the ERLE by 10 dB at low to medium Loudspeaker volumes. |