Multi-Task Sub-Band Network For Deep Residual Echo Suppression

2023/03/11 by Jiayao Sun, Sun, Jiayao, Dawei Luo +9 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #Music and Audio Processing #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2303.06404

openalex publication_date 2023/03/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper introduces the SWANT team entry to the ICASSP 2023 AEC Challenge. We submit a system that cascades a linear filter with a neural post-filter. Particularly, we adopt sub-band processing to handle full-band signals and shape the network with multi-task learning, where dual signal voice activity detection (DSVAD) and echo estimation are adopted as auxiliary tasks. Moreover, we particularly improve the time frequency convolution module (TFCM) to increase the receptive field using small convolution kernels. Finally, our system has ranked 4th in ICASSP 2023 AEC Challenge Non-personalized track.

Cited by

• EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation

Related

• Two-step Band-split Neural Network Approach for Full-band Residual Echo Suppression
• Residual acoustic echo suppression based on efficient multi-task convolutional neural network
• Y²-Net FCRN for Acoustic Echo and Noise Suppression
• EchoFilter: End-to-End Neural Network for Acoustic Echo Cancellation
• NN3A: Neural Network supported Acoustic Echo Cancellation, Noise Suppression and Automatic Gain Control for Real-Time Communications