Deep Adaptive Aec: Hybrid of Deep Learning and Adaptive Acoustic Echo Cancellation
Hao Zhang, Srivatsan Kandadai, Harsha I. K. Rao, Minje Kim, Tarun Pruthi, Trausti Kristjansson
Abstract
In this paper we integrate classic adaptive filtering algorithms with modern deep learning to propose a new approach called deep adaptive AEC. The main idea is to represent the linear adaptive algorithm as a differentiable layer within a deep neural network (DNN) framework. This enables the gradients to flow through the adaptive layer during back propagation and the inner layers of the DNN are trained to estimate the playback reference signal and the time-varying learning factors. The proposed approach combines the power of DNNs with adaptive filters. Experimental results show the effectiveness of the proposed method in scenarios where the echo path changes continuously and signal-to-echo ratio (SER) and signal-to-noise ratio (SNR) are low. Furthermore, compared to fully DNN-based baseline methods, integrating adaptive algorithm consistently improves performance and leads to easier training using smaller models.