Weighted Recursive Least Square Filter and Neural Network based Residual Echo Suppression for the AEC-Challenge
This work addresses echo cancellation for audio communication systems, presenting an incremental improvement with a competitive benchmark result.
The paper tackled real-time acoustic echo cancellation by combining time delay compensation, a weighted recursive least square filter, and a neural network for residual echo suppression, achieving a mean subjective score of 4.00 and ranking 2nd in the AEC-Challenge.
This paper presents a real-time Acoustic Echo Cancellation (AEC) algorithm submitted to the AEC-Challenge. The algorithm consists of three modules: Generalized Cross-Correlation with PHAse Transform (GCC-PHAT) based time delay compensation, weighted Recursive Least Square (wRLS) based linear adaptive filtering and neural network based residual echo suppression. The wRLS filter is derived from a novel semi-blind source separation perspective. The neural network model predicts a Phase-Sensitive Mask (PSM) based on the aligned reference and the linear filter output. The algorithm achieved a mean subjective score of 4.00 and ranked 2nd in the AEC-Challenge.