Attention-Enhanced Short-Time Wiener Solution for Acoustic Echo Cancellation
Preprint
Abstract
Acoustic Echo Cancellation (AEC) is an essential speech signal processing technology that removes echoes from microphone inputs to facilitate natural-sounding full-duplex communication. Currently, deep learning-based AEC methods primarily focus on refining model architectures, frequently neglecting the incorporation of knowledge from traditional filter theory. This paper presents an innovative approach to AEC by introducing an attention-enhanced short-time Wiener solution. Our method strategically harnesses attention mechanisms to mitigate the impact of double-talk interference, thereby optimizing the efficiency of knowledge utilization. The derivation of the short-term Wiener solution, which adapts classical Wiener solutions to finite input causality, integrates established insights from filter theory into this method. The experimental outcomes corroborate the effectiveness of our proposed approach, surpassing other baseline models in performance and generalization. The official code is available at https://github.com/ZhaoF-i/ASTWS-AECKeywords
All Related Versions
This publication has 6 references indexed in Scilit:
- ICASSP 2023 Acoustic Echo Cancellation ChallengeIEEE Open Journal of Signal Processing, 2024
- Neuralkalman: A Learnable Kalman Filter for Acoustic Echo Cancellation2023
- Neural Multi-Channel and Multi-Microphone Acoustic Echo CancellationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
- Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- An overview on optimized NLMS algorithms for acoustic echo cancellationEURASIP Journal on Advances in Signal Processing, 2015
- Performance measurement in blind audio source separationIEEE Transactions on Audio, Speech, and Language Processing, 2006