Regression-based Residual Acoustic Echo Suppression

  title={Regression-based Residual Acoustic Echo Suppression},
  author={Amit Chhetri and Arun C. Surendran and Jack W. Stokes and John C. Platt},
In this paper, we propose a novel regression-based algorithm for suppressing the residual echo present in the output of an acoustic echo canceller (AEC). We learn a functional relationship between the magnitudes of many frames of the speaker signal and the magnitude of the echo residual, per subband. We estimate and track the parameters of this function using adaptive algorithms (e.g. NLMS). We show that this approach can be interpreted as a rank-1 approximation to a more general regression… CONTINUE READING