Adaptive Speech Quality Aware Complex Neural Network for Acoustic Echo Cancellation with Supervised Contrastive Learning

TL;DR

This paper introduces an adaptive complex neural network for real-time acoustic echo cancellation, utilizing contrastive learning and speech quality-aware loss functions to enhance performance.

Contribution

It presents a novel complex modular neural network architecture with a contrastive learning framework and speech quality-aware loss functions for improved AEC.

Findings

Outperforms state-of-the-art AEC methods

Effective in real-time echo cancellation

Improves speech quality preservation

Abstract

Acoustic echo cancellation (AEC) is designed to remove echoes, reverberation, and unwanted added sounds from the microphone signal while maintaining the quality of the near-end speaker's speech. This paper proposes adaptive speech quality complex neural networks to focus on specific tasks for real-time acoustic echo cancellation. In specific, we propose a complex modularize neural network with different stages to focus on feature extraction, acoustic separation, and mask optimization receptively. Furthermore, we adopt the contrastive learning framework and novel speech quality aware loss functions to further improve the performance. The model is trained with 72 hours for pre-training and then 72 hours for fine-tuning. The proposed model outperforms the state-of-the-art performance.