The NLMS algorithm with time-variant optimum stepsize derived from a Bayesian network perspective

TL;DR

This paper introduces a Bayesian network-based derivation of a time-variant stepsize for the NLMS algorithm, improving adaptive acoustic echo cancellation by estimating the stepsize through an EM algorithm.

Contribution

It presents a novel EM-based derivation of an adaptive stepsize for NLMS, linking Bayesian network modeling with existing optimal stepsize methods.

Findings

The EM-NLMS algorithm matches the optimal stepsize calculation.

Experimental results confirm improved adaptation in acoustic echo cancellation.

The method effectively handles different input signals like noise and speech.

Abstract

In this article, we derive a new stepsize adaptation for the normalized least mean square algorithm (NLMS) by describing the task of linear acoustic echo cancellation from a Bayesian network perspective. Similar to the well-known Kalman filter equations, we model the acoustic wave propagation from the loudspeaker to the microphone by a latent state vector and define a linear observation equation (to model the relation between the state vector and the observation) as well as a linear process equation (to model the temporal progress of the state vector). Based on additional assumptions on the statistics of the random variables in observation and process equation, we apply the expectation-maximization (EM) algorithm to derive an NLMS-like filter adaptation. By exploiting the conditional independence rules for Bayesian networks, we reveal that the resulting EM-NLMS algorithm has a stepsize update equivalent to the optimal-stepsize calculation proposed by Yamamoto and Kitayama in 1982, which has been adopted in many textbooks. As main difference, the instantaneous stepsize value is estimated in the M step of the EM algorithm (instead of being approximated by artificially extending the acoustic echo path). The EM-NLMS algorithm is experimentally verified for synthesized scenarios with both, white noise and male speech as input signal.