View in EDS

Direction of arrival estimation with neural networks via test time self-supervised optimization and array manifold sensinga).

Saved in:
Bibliographic Details
Title: Direction of arrival estimation with neural networks via test time self-supervised optimization and array manifold sensinga).
Authors: Liu, Yining1,2,3 (AUTHOR), Zhang, Xiaojun4 (AUTHOR), Luo, Ziqiang1,2,3 (AUTHOR), Wang, Zenggang1,2,3 (AUTHOR), Li, Zhenglin1,2,3 (AUTHOR), Xu, Lingji1,2,3 (AUTHOR) xulj26@mail.sysu.edu.cn
Source: Journal of the Acoustical Society of America. May2026, Vol. 159 Issue 5, p3967-3979. 13p.
Subjects: Direction of arrival estimation, Beamforming, Array processing, Machine learning, Signal processing, Artificial neural networks
Abstract: Adaptive beamformers such as the minimum-variance distortionless response (MVDR) are highly sensitive to mismatches in both the sample covariance matrix (SCM) and the array steering vector. This paper proposes a closed-loop Neural-MVDR framework for direction-of-arrival estimation that enforces a distortionless constraint consistent with a physically parameterized array model. The method requires no offline supervised pretraining on external labeled datasets. Instead, it performs per-frame, self-supervised adaptation at test time. For each incoming snapshot, it alternates among steering-vector refinement, robust SCM reconstruction parameterized by a lightweight neural module, and analytical MVDR spectral estimation. Experiments on synthetic data and the SWellEx-96 S5 event demonstrate improved robustness compared with the conventional beamformer, conventional MVDR, and representative robust MVDR variants based on eigenspace suppression, covariance matrix tapering, and oracle-approximating shrinkage, respectively. [ABSTRACT FROM AUTHOR]
Copyright of Journal of the Acoustical Society of America is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 194178255
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Direction of arrival estimation with neural networks via test time self-supervised optimization and array manifold sensinga).
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Liu%2C+Yining%22">Liu, Yining</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Xiaojun%22">Zhang, Xiaojun</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Luo%2C+Ziqiang%22">Luo, Ziqiang</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Zenggang%22">Wang, Zenggang</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Li%2C+Zhenglin%22">Li, Zhenglin</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Lingji%22">Xu, Lingji</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> xulj26@mail.sysu.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+the+Acoustical+Society+of+America%22">Journal of the Acoustical Society of America</searchLink>. May2026, Vol. 159 Issue 5, p3967-3979. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Direction+of+arrival+estimation%22">Direction of arrival estimation</searchLink><br /><searchLink fieldCode="DE" term="%22Beamforming%22">Beamforming</searchLink><br /><searchLink fieldCode="DE" term="%22Array+processing%22">Array processing</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Signal+processing%22">Signal processing</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Adaptive beamformers such as the minimum-variance distortionless response (MVDR) are highly sensitive to mismatches in both the sample covariance matrix (SCM) and the array steering vector. This paper proposes a closed-loop Neural-MVDR framework for direction-of-arrival estimation that enforces a distortionless constraint consistent with a physically parameterized array model. The method requires no offline supervised pretraining on external labeled datasets. Instead, it performs per-frame, self-supervised adaptation at test time. For each incoming snapshot, it alternates among steering-vector refinement, robust SCM reconstruction parameterized by a lightweight neural module, and analytical MVDR spectral estimation. Experiments on synthetic data and the SWellEx-96 S5 event demonstrate improved robustness compared with the conventional beamformer, conventional MVDR, and representative robust MVDR variants based on eigenspace suppression, covariance matrix tapering, and oracle-approximating shrinkage, respectively. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of the Acoustical Society of America is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194178255
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1121/10.0043732
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 3967
    Subjects:
      – SubjectFull: Direction of arrival estimation
        Type: general
      – SubjectFull: Beamforming
        Type: general
      – SubjectFull: Array processing
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Signal processing
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
    Titles:
      – TitleFull: Direction of arrival estimation with neural networks via test time self-supervised optimization and array manifold sensinga).
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Liu, Yining
      – PersonEntity:
          Name:
            NameFull: Zhang, Xiaojun
      – PersonEntity:
          Name:
            NameFull: Luo, Ziqiang
      – PersonEntity:
          Name:
            NameFull: Wang, Zenggang
      – PersonEntity:
          Name:
            NameFull: Li, Zhenglin
      – PersonEntity:
          Name:
            NameFull: Xu, Lingji
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 00014966
          Numbering:
            – Type: volume
              Value: 159
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: Journal of the Acoustical Society of America
              Type: main
ResultId 1