Low-Complexity Acoustic Echo Cancellation with Neural Kalman Filtering

07/23/2022
by   Dong Yang, et al.
0

The Kalman filter has been adopted in acoustic echo cancellation due to its robustness to double-talk, fast convergence, and good steady-state performance. The performance of Kalman filter is closely related to the estimation accuracy of the state noise covariance and the observation noise covariance. The estimation error may lead to unacceptable results, especially when the echo path suffers abrupt changes, the tracking performance of the Kalman filter could be degraded significantly. In this paper, we propose the neural Kalman filtering (NKF), which uses neural networks to implicitly model the covariance of the state noise and observation noise and to output the Kalman gain in real-time. Experimental results on both synthetic test sets and real-recorded test sets show that, the proposed NKF has superior convergence and re-convergence performance while ensuring low near-end speech degradation comparing with the state-of-the-art model-based methods. Moreover, the model size of the proposed NKF is merely 5.3 K and the RTF is as low as 0.09, which indicates that it can be deployed in low-resource platforms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/16/2020

A Synergistic Kalman- and Deep Postfiltering Approach to Acoustic Echo Cancellation

We introduce a synergistic approach to double-talk robust acoustic echo ...
research
08/25/2018

Efficient improvement of frequency-domain Kalman filter

The frequency-domain Kalman filter (FKF) has been utilized in many audio...
research
07/23/2018

A Frequency-Domain Characterization of Optimal Error Covariance for the Kalman-Bucy Filter

In this paper, we discover that the trace of the division of the optimal...
research
03/24/2020

On the Complexity and Approximability of Optimal Sensor Selection and Attack for Kalman Filtering

Given a linear dynamical system affected by stochastic noise, we conside...
research
03/31/2015

On the Projective Geometry of Kalman Filter

Convergence of the Kalman filter is best analyzed by studying the contra...
research
09/03/2021

Optimizing the Energy Efficiency of Unreliable Memories for Quantized Kalman Filtering

This paper presents a quantized Kalman filter implemented using unreliab...
research
03/01/2021

Unsupervised Classification of Voiced Speech and Pitch Tracking Using Forward-Backward Kalman Filtering

The detection of voiced speech, the estimation of the fundamental freque...

Please sign up or login with your details

Forgot password? Click here to reset