Deep Multi-task Network for Delay Estimation and Echo Cancellation

TL;DR

This paper introduces a multi-task deep learning network that simultaneously estimates echo path delay and performs echo cancellation, improving robustness and performance in scenarios with inconsistent ref-delays.

Contribution

A novel multi-task CRNN-based architecture is proposed for joint delay estimation and echo cancellation, addressing ref-delay variability and enhancing model robustness.

Findings

Outperforms state-of-the-art in echo delay estimation

Achieves higher ERLE and PESQ scores

Effective in scenarios with inconsistent ref-delays

Abstract

Echo path delay (or ref-delay) estimation is a big challenge in acoustic echo cancellation. Different devices may introduce various ref-delay in practice. Ref-delay inconsistency slows down the convergence of adaptive filters, and also degrades the performance of deep learning models due to 'unseen' ref-delays in the training set. In this paper, a multi-task network is proposed to address both ref-delay estimation and echo cancellation tasks. The proposed architecture consists of two convolutional recurrent networks (CRNNs) to estimate the echo and enhanced signals separately, as well as a fully-connected (FC) network to estimate the echo path delay. Echo signal is first predicted, and then is combined with reference signal together for delay estimation. At the end, delay compensated reference and microphone signals are used to predict the enhanced target signal. Experimental results suggest that the proposed method makes reliable delay estimation and outperforms the existing state-of-the-art solutions in inconsistent echo path delay scenarios, in terms of echo return loss enhancement (ERLE) and perceptual evaluation of speech quality (PESQ). Furthermore, a data augmentation method is studied to evaluate the model performance on different portion of synthetical data with artificially introduced ref-delay.