Collaborative block-delay Volterra filters for nonlinear acoustic echo cancellation

Abstract

A new nonlinear adaptive filtering strategy, collaborative block-delay Volterra filters (CBDVF), is proposed for nonlinear acoustic echo cancellation (NAEC). This paper focuses on the theoretical reasonability and practical feasibility of the proposed algorithm. Specifically, a practice-friendly adaptive filtering architecture is designed to ensure that the linear filter is considered a priority to play the most important role in estimating the echo path while the nonlinear filters will further perfect the modeling nonlinearities. A CBDVF is obtained by a combination of linear filter and different nonlinear filtering blocks of different time-delay length, where the nonlinear time-delay blocks are activated or deactivated automatically and adaptively to fulfil their tasks via some adaptive shrinkage factors. Theoretical performance analysis is also conducted to characterize the stability condition of the proposed algorithm. Simulations with an acoustic echo cancellation problem demonstrate the effectiveness of the proposed CBDVF. Moreover, the evaluation for CBDVF is completed for a real NAEC scenario.