View in EDS

Fast grid-free strength mapping of multiple sound sources from microphone array data using a Transformer architecture.

Saved in:
Bibliographic Details
Title: Fast grid-free strength mapping of multiple sound sources from microphone array data using a Transformer architecture.
Authors: Kujawski, Adam1 (AUTHOR) adam.kujawski@tu-berlin.de, Sarradj, Ennes1 (AUTHOR)
Source: Journal of the Acoustical Society of America. Nov2022, Vol. 152 Issue 5, p2543-2556. 14p.
Subjects: Microphone arrays, Deep learning
Abstract: Conventional microphone array methods for the characterization of sound sources that require a focus-grid are, depending on the grid resolution, either computationally demanding or limited in reconstruction accuracy. This paper presents a deep learning method for grid-free source characterization using a Transformer architecture that is exclusively trained with simulated data. Unlike previous grid-free model architectures, the presented approach requires a single model to characterize an unknown number of ground-truth sources. The model predicts a set of source components, spatially arranged in clusters. Integration over the predicted cluster components allows for the determination of the strength for each ground-truth source individually. Fast and accurate source mapping performance of up to ten sources at different frequencies is demonstrated and strategies to reduce the training effort at neighboring frequencies are given. A comparison with the established grid-based CLEAN-SC and a probabilistic sparse Bayesian learning method on experimental data emphasizes the validity of the approach. [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: 160542806
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Fast grid-free strength mapping of multiple sound sources from microphone array data using a Transformer architecture.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Kujawski%2C+Adam%22">Kujawski, Adam</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> adam.kujawski@tu-berlin.de</i><br /><searchLink fieldCode="AR" term="%22Sarradj%2C+Ennes%22">Sarradj, Ennes</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– 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>. Nov2022, Vol. 152 Issue 5, p2543-2556. 14p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Microphone+arrays%22">Microphone arrays</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Conventional microphone array methods for the characterization of sound sources that require a focus-grid are, depending on the grid resolution, either computationally demanding or limited in reconstruction accuracy. This paper presents a deep learning method for grid-free source characterization using a Transformer architecture that is exclusively trained with simulated data. Unlike previous grid-free model architectures, the presented approach requires a single model to characterize an unknown number of ground-truth sources. The model predicts a set of source components, spatially arranged in clusters. Integration over the predicted cluster components allows for the determination of the strength for each ground-truth source individually. Fast and accurate source mapping performance of up to ten sources at different frequencies is demonstrated and strategies to reduce the training effort at neighboring frequencies are given. A comparison with the established grid-based CLEAN-SC and a probabilistic sparse Bayesian learning method on experimental data emphasizes the validity of the approach. [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=160542806
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1121/10.0015005
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 14
        StartPage: 2543
    Subjects:
      – SubjectFull: Microphone arrays
        Type: general
      – SubjectFull: Deep learning
        Type: general
    Titles:
      – TitleFull: Fast grid-free strength mapping of multiple sound sources from microphone array data using a Transformer architecture.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Kujawski, Adam
      – PersonEntity:
          Name:
            NameFull: Sarradj, Ennes
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 11
              Text: Nov2022
              Type: published
              Y: 2022
          Identifiers:
            – Type: issn-print
              Value: 00014966
          Numbering:
            – Type: volume
              Value: 152
            – Type: issue
              Value: 5
          Titles:
            – TitleFull: Journal of the Acoustical Society of America
              Type: main
ResultId 1