Deep Adaptation Control for Stereophonic Acoustic Echo Cancellation

We introduce a general and data-driven adaptation-control framework for stereophonic acoustic-echo cancellation. The adaptation update rule for the filters that estimate the actual echo paths is compactly expressed with the widely-linear model in the complex time domain. A single step-size parameter...

Full description

Saved in:
Bibliographic Details
Main Authors: Ivry, Amir, Cohen, Israel, Berdugo, Baruch
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
adaptation control
Adaptation models
Adaptive filters
deep learning
Echo cancellers
Filtering
Real-time systems
sign-error NLMS
Signal processing
Stereophonic acoustic echo cancellation
variable step-size
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce a general and data-driven adaptation-control framework for stereophonic acoustic-echo cancellation. The adaptation update rule for the filters that estimate the actual echo paths is compactly expressed with the widely-linear model in the complex time domain. A single step-size parameter that governs the behavior of the adaptation process is optimized by minimizing the misalignment between the actual echo paths and their filtered estimate. The relation between acoustic signals and the optimal step-size is learned via a deep neural network. In test mode, the optimal step-size prediction is inferred by the network and fed to the sign-error nor-malized least mean-squares (SNLMS) adaptive filter for echo-paths tracking. Real and simulated data show advantageous performance in single and double-talk scenarios across various acoustic setups.
ISSN:1947-1629
DOI:10.1109/WASPAA58266.2023.10248161