F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement

TL;DR

This paper introduces a real-time complex neural network model using frequency-time-LSTMs for improved acoustic echo cancellation and speech enhancement, outperforming existing baselines in noisy and reverberant conditions.

Contribution

It proposes a novel F-T-LSTM based complex neural network for joint AEC and speech enhancement, with a modified SI-SNR loss function for better performance.

Findings

Outperforms baseline by 0.27 MOS

Uses only 1.4 million parameters

Effective in noisy and reverberant environments

Abstract

With the increasing demand for audio communication and online conference, ensuring the robustness of Acoustic Echo Cancellation (AEC) under the complicated acoustic scenario including noise, reverberation and nonlinear distortion has become a top issue. Although there have been some traditional methods that consider nonlinear distortion, they are still inefficient for echo suppression and the performance will be attenuated when noise is present. In this paper, we present a real-time AEC approach using complex neural network to better modeling the important phase information and frequency-time-LSTMs (F-T-LSTM), which scan both frequency and time axis, for better temporal modeling. Moreover, we utilize modified SI-SNR as cost function to make the model to have better echo cancellation and noise suppression (NS) performance. With only 1.4M parameters, the proposed approach outperforms the AEC-challenge baseline by 0.27 in terms of Mean Opinion Score (MOS).