Experimental Results of Underwater Sound Speed Profile Inversion by Few-shot Multi-task Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Wei, Gao, Fan, Wang, Junting, Zhang, Hao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909555495010304
author Huang, Wei
Gao, Fan
Wang, Junting
Zhang, Hao
author_facet Huang, Wei
Gao, Fan
Wang, Junting
Zhang, Hao
contents Underwater Sound Speed Profile (SSP) distribution has great influence on the propagation mode of acoustic signal, thus the fast and accurate estimation of SSP is of great importance in building underwater observation systems. The state-of-the-art SSP inversion methods include frameworks of matched field processing (MFP), compressive sensing (CS), and feedforeward neural networks (FNN), among which the FNN shows better real-time performance while maintain the same level of accuracy. However, the training of FNN needs quite a lot historical SSP samples, which is diffcult to be satisfied in many ocean areas. This situation is called few-shot learning. To tackle this issue, we propose a multi-task learning (MTL) model with partial parameter sharing among different traning tasks. By MTL, common features could be extracted, thus accelerating the learning process on given tasks, and reducing the demand for reference samples, so as to enhance the generalization ability in few-shot learning. To verify the feasibility and effectiveness of MTL, a deep-ocean experiment was held in April 2023 at the South China Sea. Results shows that MTL outperforms the state-of-the-art methods in terms of accuracy for SSP inversion, while inherits the real-time advantage of FNN during the inversion stage.
format Preprint
id arxiv_https___arxiv_org_abs_2310_11708
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Experimental Results of Underwater Sound Speed Profile Inversion by Few-shot Multi-task Learning
Huang, Wei
Gao, Fan
Wang, Junting
Zhang, Hao
Audio and Speech Processing
Sound
Underwater Sound Speed Profile (SSP) distribution has great influence on the propagation mode of acoustic signal, thus the fast and accurate estimation of SSP is of great importance in building underwater observation systems. The state-of-the-art SSP inversion methods include frameworks of matched field processing (MFP), compressive sensing (CS), and feedforeward neural networks (FNN), among which the FNN shows better real-time performance while maintain the same level of accuracy. However, the training of FNN needs quite a lot historical SSP samples, which is diffcult to be satisfied in many ocean areas. This situation is called few-shot learning. To tackle this issue, we propose a multi-task learning (MTL) model with partial parameter sharing among different traning tasks. By MTL, common features could be extracted, thus accelerating the learning process on given tasks, and reducing the demand for reference samples, so as to enhance the generalization ability in few-shot learning. To verify the feasibility and effectiveness of MTL, a deep-ocean experiment was held in April 2023 at the South China Sea. Results shows that MTL outperforms the state-of-the-art methods in terms of accuracy for SSP inversion, while inherits the real-time advantage of FNN during the inversion stage.
title Experimental Results of Underwater Sound Speed Profile Inversion by Few-shot Multi-task Learning
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2310.11708