Semi-blind source separation using convolutive transfer function for nonlinear acoustic echo cancellation

TL;DR

This paper introduces improved semi-blind source separation methods for nonlinear acoustic echo cancellation using convolutive transfer function approximation, achieving better performance in reverberant environments.

Contribution

It proposes two new SBSS methods based on AuxIVA and ILRMA with CTF approximation, enhancing real-time applicability and echo cancellation effectiveness.

Findings

Significantly improved echo cancellation performance.

Effective modeling of long impulse responses with short latency.

Better stability and convergence in reverberant environments.

Abstract

The recently proposed semi-blind source separation (SBSS) method for nonlinear acoustic echo cancellation (NAEC) outperforms adaptive NAEC in attenuating the nonlinear acoustic echo. However, the multiplicative transfer function (MTF) approximation makes it unsuitable for real-time applications especially in highly reverberant environments, and the natural gradient makes it hard to balance well between fast convergence speed and stability. In this paper, we propose two more effective SBSS methods based on auxiliary-function-based independent vector analysis (AuxIVA) and independent low-rank matrix analysis (ILRMA). The convolutive transfer function (CTF) approximation is used instead of MTF so that a long impulse response can be modeled with a short latency. The optimization schemes used in AuxIVA and ILRMA are carefully regularized according to the constrained demixing matrix of NAEC. Experimental results validate significantly better echo cancellation performance of the proposed methods.