Acoustic Echo Cancellation by Combining Adaptive Digital Filter and Recurrent Neural Network

Abstract

Acoustic Echo Cancellation (AEC) plays a key role in voice interaction. Due to the explicit mathematical principle and intelligent nature to accommodate conditions, adaptive filters with different types of implementations are always used for AEC, giving considerable performance. However, there would be some kinds of residual echo in the results, including linear residue introduced by mismatching between estimation and the reality and non-linear residue mostly caused by non-linear components on the audio devices. The linear residue can be reduced with elaborate structure and methods, leaving the non-linear residue intractable for suppression. Though, some non-linear processing methods have already be raised, they are complicated and inefficient for suppression, and would bring damage to the speech audio. In this paper, a fusion scheme by combining adaptive filter and neural network is proposed for AEC. The echo could be reduced in a large scale by adaptive filtering, resulting in little residual echo. Though it is much smaller than speech audio, it could also be perceived by human ear and would make communication annoy. The neural network is elaborately designed and trained for suppressing such residual echo. Experiments compared with prevailing methods are conducted, validating the effectiveness and superiority of the proposed combination scheme.

ICASSP 2021 Acoustic Echo Cancellation Challenge: Datasets, Testing Framework, and Results

“…With the advent of deep learning techniques, several supervised learning algorithms for AEC have shown better performance compared to their classical counterparts [2,3,4]. Some studies have also shown good performance using a combination of classical and deep learning methods such as using adaptive filters and recurrent neural networks (RNNs) [4,5] AEC models, there has been no evidence of their performance on real-world datasets with speech recorded in diverse noise and reverberant environments. This makes it difficult for researchers in the industry to choose a good model that can perform well on a representative real-world dataset.…”

Auto-DSP: Learning to Optimize Acoustic Echo Cancellers

“…Customized AEC adaptive filters take many forms including algorithms based on sparsity [6], adaptive normalization [7], and adaptive learning-rates [8], as well as data-driven approaches for selecting learning rates automatically [9,10] and based on a meta-stepsize [11,12]. More recently, deep learning techniques have been used as AEC sub-components including learned residual echo suppressors [13,14,15], double-talk detectors [16], and nonlinear distortions blocks [17,18,19,20,21]. These approaches, however, commonly do not use neural network modules that adapt at test In the machine learning literature, there have been exciting developments in meta-learning, automatic machine learning, and learning how to learn methods.…”

Multi-Scale Attention Neural Network for Acoustic Echo Cancellation

“…To overcome this problem, numeric methods have been proposed, such as Nonlinear AEC (NLAEC) method where a set of nonlinear basis functions are used for AEC [9,10,11] and nonlinear post-filtering method where an additional nonlinear processing module is cascaded for residual echo suppression [12,13,14,15]. Recently, since its great potential in speech processing tasks, neural network (NN) has been used for AEC, such as NN-based post-filtering method where NN is used for residual echo suppression instead of conventional post-filters [16], NN-based NLAEC method where NN is used for modeling nonlinear echo [17], separation-based method where source separation with an additional information from the far-end [18] is used for AEC, NN-based adaptive filtering method where the structure of AF is adopted for designing AEC network [19,20].…”