End-To-End Deep Learning-Based Adaptation Control for Frequency-Domain Adaptive System Identification

Haubner T, Brendel A, Kellermann W (2022)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2022

Event location: Singapur SG

DOI: 10.1109/ICASSP43922.2022.9747334

Open Access Link: https://arxiv.org/abs/2106.01262

Abstract

We present a novel end-to-end deep learning-based adaptation control algorithm for frequency-domain adaptive system identification. The proposed method exploits a deep neural network to map observed signal features to corresponding step-sizes which control the filter adaptation. The parameters of the network are optimized in an end-to-end fashion by minimizing the average normalized system distance of the adaptive filter. This avoids the need of explicit signal power spectral density estimation as required for model-based adaptation control and further auxiliary mechanisms to deal with model inaccuracies. The proposed algorithm achieves fast convergence and robust steady-state performance for scenarios characterized by high-level, non-white and non-stationary additive noise signals, abrupt environment changes and additional model inaccuracies.

Authors with CRIS profile

Thomas Haubner Professur für Signalverarbeitung Andreas Brendel Professur für Signalverarbeitung Walter Kellermann Professur für Signalverarbeitung

How to cite

APA:

Haubner, T., Brendel, A., & Kellermann, W. (2022). End-To-End Deep Learning-Based Adaptation Control for Frequency-Domain Adaptive System Identification. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Singapur, SG.

MLA:

Haubner, Thomas, Andreas Brendel, and Walter Kellermann. "End-To-End Deep Learning-Based Adaptation Control for Frequency-Domain Adaptive System Identification." Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapur 2022.

BibTeX: Download