Advancing Acoustic Howling Suppression through Recursive Training of Neural Networks

TL;DR

This paper presents a recursive training framework for neural networks to improve acoustic howling suppression, closely mimicking real-world streaming conditions and integrating traditional filtering methods for enhanced performance.

Contribution

The paper introduces a novel recursive training approach that better aligns neural network training with real-world acoustic howling suppression scenarios, including hybrid methods with Kalman filters.

Findings

Significant improvement over previous methods in suppressing acoustic howling.

Effective strategies for howling detection and initialization enhance training efficiency.

Framework bridges the gap between training and real-world inference in AHS.

Abstract

In this paper, we introduce a novel training framework designed to comprehensively address the acoustic howling issue by examining its fundamental formation process. This framework integrates a neural network (NN) module into the closed-loop system during training with signals generated recursively on the fly to closely mimic the streaming process of acoustic howling suppression (AHS). The proposed recursive training strategy bridges the gap between training and real-world inference scenarios, marking a departure from previous NN-based methods that typically approach AHS as either noise suppression or acoustic echo cancellation. Within this framework, we explore two methodologies: one exclusively relying on NN and the other combining NN with the traditional Kalman filter. Additionally, we propose strategies, including howling detection and initialization using pre-trained offline models, to bolster trainability and expedite the training process. Experimental results validate that this framework offers a substantial improvement over previous methodologies for acoustic howling suppression.