Fast ship radiated noise recognition using three-dimensional mel-spectrograms with an additive attention based transformer
Passive recognition of ship-radiated noise plays a crucial role in military and economic domains. However, underwater environments pose significant challenges due to inherent noise, reverberation, and time-varying acoustic channels. This paper introduces a novel approach for ship target recognition...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-11-01
|
Series: | Frontiers in Marine Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2023.1280708/full |
_version_ | 1797463630443184128 |
---|---|
author | Yan Wang Hao Zhang Wei Huang |
author_facet | Yan Wang Hao Zhang Wei Huang |
author_sort | Yan Wang |
collection | DOAJ |
description | Passive recognition of ship-radiated noise plays a crucial role in military and economic domains. However, underwater environments pose significant challenges due to inherent noise, reverberation, and time-varying acoustic channels. This paper introduces a novel approach for ship target recognition and classification by leveraging the power of three-dimensional (3D) Mel-spectrograms and an additive attention based Transformer (ADDTr). The proposed method utilizes 3D Mel-spectrograms to capture the temporal variations in both target signal and ambient noise, thereby enhancing both categories’ distinguishable characteristics. By incorporating an additional spatial dimension, the modeling of reverberation effects becomes possible. Through analysis of spatial patterns and changes within the spectrograms, distortions caused by reverberation can be estimated and compensated, so that the clarity of the target signals can be improved. The proposed ADDTr leverages an additive attention mechanism to focus on informative acoustic features while suppressing the influence of noisy or distorted components. This attention-based approach not only enhances the discriminative power of the model but also accelerates the recognition process. It efficiently captures both temporal and spatial dependencies, enabling accurate analysis of complex acoustic signals and precise predictions. Comprehensive comparisons with state-of-the-art acoustic target recognition models on the ShipsEar dataset demonstrate the superiority of the proposed ADDTr approach. Achieving an accuracy of 96.82% with the lowest computation costs, ADDTr outperforms other models. |
first_indexed | 2024-03-09T17:53:30Z |
format | Article |
id | doaj.art-9e7fac882c1d477e8bee5a1fd6ba3903 |
institution | Directory Open Access Journal |
issn | 2296-7745 |
language | English |
last_indexed | 2024-03-09T17:53:30Z |
publishDate | 2023-11-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Marine Science |
spelling | doaj.art-9e7fac882c1d477e8bee5a1fd6ba39032023-11-24T10:31:15ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452023-11-011010.3389/fmars.2023.12807081280708Fast ship radiated noise recognition using three-dimensional mel-spectrograms with an additive attention based transformerYan WangHao ZhangWei HuangPassive recognition of ship-radiated noise plays a crucial role in military and economic domains. However, underwater environments pose significant challenges due to inherent noise, reverberation, and time-varying acoustic channels. This paper introduces a novel approach for ship target recognition and classification by leveraging the power of three-dimensional (3D) Mel-spectrograms and an additive attention based Transformer (ADDTr). The proposed method utilizes 3D Mel-spectrograms to capture the temporal variations in both target signal and ambient noise, thereby enhancing both categories’ distinguishable characteristics. By incorporating an additional spatial dimension, the modeling of reverberation effects becomes possible. Through analysis of spatial patterns and changes within the spectrograms, distortions caused by reverberation can be estimated and compensated, so that the clarity of the target signals can be improved. The proposed ADDTr leverages an additive attention mechanism to focus on informative acoustic features while suppressing the influence of noisy or distorted components. This attention-based approach not only enhances the discriminative power of the model but also accelerates the recognition process. It efficiently captures both temporal and spatial dependencies, enabling accurate analysis of complex acoustic signals and precise predictions. Comprehensive comparisons with state-of-the-art acoustic target recognition models on the ShipsEar dataset demonstrate the superiority of the proposed ADDTr approach. Achieving an accuracy of 96.82% with the lowest computation costs, ADDTr outperforms other models.https://www.frontiersin.org/articles/10.3389/fmars.2023.1280708/fullunderwater acoustic target recognitiondeep learningadditive attention based transformer3D mel-spectrogramship radiated noise |
spellingShingle | Yan Wang Hao Zhang Wei Huang Fast ship radiated noise recognition using three-dimensional mel-spectrograms with an additive attention based transformer Frontiers in Marine Science underwater acoustic target recognition deep learning additive attention based transformer 3D mel-spectrogram ship radiated noise |
title | Fast ship radiated noise recognition using three-dimensional mel-spectrograms with an additive attention based transformer |
title_full | Fast ship radiated noise recognition using three-dimensional mel-spectrograms with an additive attention based transformer |
title_fullStr | Fast ship radiated noise recognition using three-dimensional mel-spectrograms with an additive attention based transformer |
title_full_unstemmed | Fast ship radiated noise recognition using three-dimensional mel-spectrograms with an additive attention based transformer |
title_short | Fast ship radiated noise recognition using three-dimensional mel-spectrograms with an additive attention based transformer |
title_sort | fast ship radiated noise recognition using three dimensional mel spectrograms with an additive attention based transformer |
topic | underwater acoustic target recognition deep learning additive attention based transformer 3D mel-spectrogram ship radiated noise |
url | https://www.frontiersin.org/articles/10.3389/fmars.2023.1280708/full |
work_keys_str_mv | AT yanwang fastshipradiatednoiserecognitionusingthreedimensionalmelspectrogramswithanadditiveattentionbasedtransformer AT haozhang fastshipradiatednoiserecognitionusingthreedimensionalmelspectrogramswithanadditiveattentionbasedtransformer AT weihuang fastshipradiatednoiserecognitionusingthreedimensionalmelspectrogramswithanadditiveattentionbasedtransformer |