A Bayesian network viewon linear and nonlinear acoustic echo cancellation
Roland Maas, Christian Huemmer, Andreas Schwarz, Christian H. Hofmann, Walter Kellermann · 2014
In this contribution, we provide a new derivation of the normalized least mean square (NLMS) algorithm from a machine learning perspective. By applying the inference rules of Bayesian networks to a linear observation model, the NLMS can be shown to arise as a modification of the Kalman filter equations. Based on a nonlinear observation model, we exemplify the benefit of the Bayesian point of view by employing the technique of particle filtering to realize a tractable algorithm for nonlinear acoustic echo cancellation. Experiments carried out on real smartphone recordings reveal the remarkable performance of the new approach.