An Exploration of Task-decoupling on Two-stage Neural Post Filter for Real-time Personalized Acoustic Echo Cancellation

TL;DR

This paper introduces a two-stage task-decoupling post-filter for personalized acoustic echo cancellation, utilizing multi-scale speaker representations to improve performance over joint models in real-time applications.

Contribution

It proposes a novel two-stage task-decoupling approach with multi-scale speaker features, enhancing PAEC effectiveness compared to traditional joint models.

Findings

Task-decoupling outperforms joint network models.

Decoupling echo cancellation from noise suppression yields better results.

Optimal training strategies are identified for the two-stage model.

Abstract

Deep learning based techniques have been popularly adopted in acoustic echo cancellation (AEC). Utilization of speaker representation has extended the frontier of AEC, thus attracting many researchers' interest in personalized acoustic echo cancellation (PAEC). Meanwhile, task-decoupling strategies are widely adopted in speech enhancement. To further explore the task-decoupling approach, we propose to use a two-stage task-decoupling post-filter (TDPF) in PAEC. Furthermore, a multi-scale local-global speaker representation is applied to improve speaker extraction in PAEC. Experimental results indicate that the task-decoupling model can yield better performance than a single joint network. The optimal approach is to decouple the echo cancellation from noise and interference speech suppression. Based on the task-decoupling sequence, optimal training strategies for the two-stage model are explored afterwards.