A Novel Deep Learning Framework for Efficient Multichannel Acoustic Feedback Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Yuan-Kuei, Azcarreta, Juan, Patel, Kashyap, Xu, Buye, Lee, Jung-Suk, Lee, Sanha, Pandey, Ashutosh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915312349216768
author Wu, Yuan-Kuei
Azcarreta, Juan
Patel, Kashyap
Xu, Buye
Lee, Jung-Suk
Lee, Sanha
Pandey, Ashutosh
author_facet Wu, Yuan-Kuei
Azcarreta, Juan
Patel, Kashyap
Xu, Buye
Lee, Jung-Suk
Lee, Sanha
Pandey, Ashutosh
contents This study presents a deep-learning framework for controlling multichannel acoustic feedback in audio devices. Traditional digital signal processing methods struggle with convergence when dealing with highly correlated noise such as feedback. We introduce a Convolutional Recurrent Network that efficiently combines spatial and temporal processing, significantly enhancing speech enhancement capabilities with lower computational demands. Our approach utilizes three training methods: In-a-Loop Training, Teacher Forcing, and a Hybrid strategy with a Multichannel Wiener Filter, optimizing performance in complex acoustic environments. This scalable framework offers a robust solution for real-world applications, making significant advances in Acoustic Feedback Control technology.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15914
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Novel Deep Learning Framework for Efficient Multichannel Acoustic Feedback Control
Wu, Yuan-Kuei
Azcarreta, Juan
Patel, Kashyap
Xu, Buye
Lee, Jung-Suk
Lee, Sanha
Pandey, Ashutosh
Sound
Audio and Speech Processing
This study presents a deep-learning framework for controlling multichannel acoustic feedback in audio devices. Traditional digital signal processing methods struggle with convergence when dealing with highly correlated noise such as feedback. We introduce a Convolutional Recurrent Network that efficiently combines spatial and temporal processing, significantly enhancing speech enhancement capabilities with lower computational demands. Our approach utilizes three training methods: In-a-Loop Training, Teacher Forcing, and a Hybrid strategy with a Multichannel Wiener Filter, optimizing performance in complex acoustic environments. This scalable framework offers a robust solution for real-world applications, making significant advances in Acoustic Feedback Control technology.
title A Novel Deep Learning Framework for Efficient Multichannel Acoustic Feedback Control
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2505.15914