Method of Underwater Acoustic Signal Denoising Based on Dual-Path Transformer Network

The presence of natural ambient noise interferes with the system for locating and identifying underwater targets. This paper suggests that a Dual-Path Transformation Network (DPTN) reduces ambient noise in underwater acoustic signals. First, the input acoustic signals’ higher-order non-li...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongqiang Song, Feng Liu, Tongsheng Shen
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9963926/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849690075470757888
author Yongqiang Song
Feng Liu
Tongsheng Shen
author_facet Yongqiang Song
Feng Liu
Tongsheng Shen
author_sort Yongqiang Song
collection DOAJ
description The presence of natural ambient noise interferes with the system for locating and identifying underwater targets. This paper suggests that a Dual-Path Transformation Network (DPTN) reduces ambient noise in underwater acoustic signals. First, the input acoustic signals’ higher-order non-linear features are extracted using a multi-scale convolutional encoder neural network. Second, sub-vectors with the same length are created according to the time dimension from the higher-order non-linear features. The sub-vectors are stitched together to form a three-dimensional tensor. Third, a neural network transformer based on the feed-forward network is constructed. Further, to capture long-term series features and separate the target signal from the noisy signals, the three-dimensional tensor is used as the input of the transformer-based masking network. Finally, overlap-add and transpose are used to obtain discernible target signals. The experimental results verify the effectiveness of the proposed underwater acoustic signal denoising algorithm and demonstrate that the proposed DPRN method can obtain higher output signal-to-noise ratio (SNR) and the scale-invariant signal-to-noise ratio (SI-SNR) compared with the other classical algorithms.
format Article
id doaj-art-febdc4b3ecd446c7aecca1cfc8bb5adb
institution DOAJ
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-febdc4b3ecd446c7aecca1cfc8bb5adb2025-08-20T03:21:26ZengIEEEIEEE Access2169-35362024-01-0112814838149410.1109/ACCESS.2022.32247529963926Method of Underwater Acoustic Signal Denoising Based on Dual-Path Transformer NetworkYongqiang Song0https://orcid.org/0000-0001-5193-5314Feng Liu1Tongsheng Shen2National Innovation Institute of Defense Technology, Beijing, ChinaChinese Academy of Military Sciences, Beijing, ChinaChinese Academy of Military Sciences, Beijing, ChinaThe presence of natural ambient noise interferes with the system for locating and identifying underwater targets. This paper suggests that a Dual-Path Transformation Network (DPTN) reduces ambient noise in underwater acoustic signals. First, the input acoustic signals’ higher-order non-linear features are extracted using a multi-scale convolutional encoder neural network. Second, sub-vectors with the same length are created according to the time dimension from the higher-order non-linear features. The sub-vectors are stitched together to form a three-dimensional tensor. Third, a neural network transformer based on the feed-forward network is constructed. Further, to capture long-term series features and separate the target signal from the noisy signals, the three-dimensional tensor is used as the input of the transformer-based masking network. Finally, overlap-add and transpose are used to obtain discernible target signals. The experimental results verify the effectiveness of the proposed underwater acoustic signal denoising algorithm and demonstrate that the proposed DPRN method can obtain higher output signal-to-noise ratio (SNR) and the scale-invariant signal-to-noise ratio (SI-SNR) compared with the other classical algorithms.https://ieeexplore.ieee.org/document/9963926/Deep learningunderwater acousticsdual-path transformer network
spellingShingle Yongqiang Song
Feng Liu
Tongsheng Shen
Method of Underwater Acoustic Signal Denoising Based on Dual-Path Transformer Network
IEEE Access
Deep learning
underwater acoustics
dual-path transformer network
title Method of Underwater Acoustic Signal Denoising Based on Dual-Path Transformer Network
title_full Method of Underwater Acoustic Signal Denoising Based on Dual-Path Transformer Network
title_fullStr Method of Underwater Acoustic Signal Denoising Based on Dual-Path Transformer Network
title_full_unstemmed Method of Underwater Acoustic Signal Denoising Based on Dual-Path Transformer Network
title_short Method of Underwater Acoustic Signal Denoising Based on Dual-Path Transformer Network
title_sort method of underwater acoustic signal denoising based on dual path transformer network
topic Deep learning
underwater acoustics
dual-path transformer network
url https://ieeexplore.ieee.org/document/9963926/
work_keys_str_mv AT yongqiangsong methodofunderwateracousticsignaldenoisingbasedondualpathtransformernetwork
AT fengliu methodofunderwateracousticsignaldenoisingbasedondualpathtransformernetwork
AT tongshengshen methodofunderwateracousticsignaldenoisingbasedondualpathtransformernetwork