Hybrid AHS: A Hybrid of Kalman Filter and Deep Learning for Acoustic Howling Suppression

TL;DR

This paper introduces a hybrid acoustic howling suppression method combining Kalman filtering and deep learning, addressing the mismatch issue in streaming inference and demonstrating superior performance over existing baselines.

Contribution

The paper presents a novel hybrid approach that integrates Kalman filter with a self-attentive recurrent neural network for robust and efficient acoustic howling suppression.

Findings

Outperforms baseline methods in suppressing howling.

Effective in both offline and streaming inference scenarios.

Works well with simulated and real-recorded data.

Abstract

Deep learning has been recently introduced for efficient acoustic howling suppression (AHS). However, the recurrent nature of howling creates a mismatch between offline training and streaming inference, limiting the quality of enhanced speech. To address this limitation, we propose a hybrid method that combines a Kalman filter with a self-attentive recurrent neural network (SARNN) to leverage their respective advantages for robust AHS. During offline training, a pre-processed signal obtained from the Kalman filter and an ideal microphone signal generated via teacher-forced training strategy are used to train the deep neural network (DNN). During streaming inference, the DNN's parameters are fixed while its output serves as a reference signal for updating the Kalman filter. Evaluation in both offline and streaming inference scenarios using simulated and real-recorded data shows that the proposed method efficiently suppresses howling and consistently outperforms baselines.