View in EDS HTML Full Text PDF Full Text

An attention-gating recurrent working memory architecture for emergent speech representation.

Saved in:
Bibliographic Details
Title: An attention-gating recurrent working memory architecture for emergent speech representation.
Authors: Elshaw, Mark (AUTHOR), Moore, RogerK. (AUTHOR), Klein, Michael (AUTHOR)
Source: Connection Science. Jun2010, Vol. 22 Issue 2, p157-175. 19p. 8 Diagrams, 2 Charts, 1 Graph.
Subjects: Artificial neural networks, Memory maps (Computer science), Cognition, Memory, Recognition (Psychology), Learning
Abstract: This paper describes an attention-gating recurrent self-organising map approach for emergent speech representation. Inspired by evidence from human cognitive processing, the architecture combines two main neural components. The first component, the attention-gating mechanism, uses actor-critic learning to perform selective attention towards speech. Through this selective attention approach, the attention-gating mechanism controls access to working memory processing. The second component, the recurrent self-organising map memory, develops a temporal-distributed representation of speech using phone-like structures. Representing speech in terms of phonetic features in an emergent self-organised fashion, according to research on child cognitive development, recreates the approach found in infants. Using this representational approach, in a fashion similar to infants, should improve the performance of automatic recognition systems through aiding speech segmentation and fast word learning. [ABSTRACT FROM AUTHOR]
Copyright of Connection Science is the property of Taylor & Francis Ltd 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: Psychology and Behavioral Sciences Collection
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: pbh
DbLabel: Psychology and Behavioral Sciences Collection
An: 50529461
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: An attention-gating recurrent working memory architecture for emergent speech representation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Elshaw%2C+Mark%22">Elshaw, Mark</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Moore%2C+RogerK%2E%22">Moore, RogerK.</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Klein%2C+Michael%22">Klein, Michael</searchLink> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Connection+Science%22">Connection Science</searchLink>. Jun2010, Vol. 22 Issue 2, p157-175. 19p. 8 Diagrams, 2 Charts, 1 Graph.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Memory+maps+%28Computer+science%29%22">Memory maps (Computer science)</searchLink><br /><searchLink fieldCode="DE" term="%22Cognition%22">Cognition</searchLink><br /><searchLink fieldCode="DE" term="%22Memory%22">Memory</searchLink><br /><searchLink fieldCode="DE" term="%22Recognition+%28Psychology%29%22">Recognition (Psychology)</searchLink><br /><searchLink fieldCode="DE" term="%22Learning%22">Learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This paper describes an attention-gating recurrent self-organising map approach for emergent speech representation. Inspired by evidence from human cognitive processing, the architecture combines two main neural components. The first component, the attention-gating mechanism, uses actor-critic learning to perform selective attention towards speech. Through this selective attention approach, the attention-gating mechanism controls access to working memory processing. The second component, the recurrent self-organising map memory, develops a temporal-distributed representation of speech using phone-like structures. Representing speech in terms of phonetic features in an emergent self-organised fashion, according to research on child cognitive development, recreates the approach found in infants. Using this representational approach, in a fashion similar to infants, should improve the performance of automatic recognition systems through aiding speech segmentation and fast word learning. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Connection Science is the property of Taylor & Francis Ltd 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=pbh&AN=50529461
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/09540090903431673
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
        StartPage: 157
    Subjects:
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Memory maps (Computer science)
        Type: general
      – SubjectFull: Cognition
        Type: general
      – SubjectFull: Memory
        Type: general
      – SubjectFull: Recognition (Psychology)
        Type: general
      – SubjectFull: Learning
        Type: general
    Titles:
      – TitleFull: An attention-gating recurrent working memory architecture for emergent speech representation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Elshaw, Mark
      – PersonEntity:
          Name:
            NameFull: Moore, RogerK.
      – PersonEntity:
          Name:
            NameFull: Klein, Michael
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2010
              Type: published
              Y: 2010
          Identifiers:
            – Type: issn-print
              Value: 09540091
          Numbering:
            – Type: volume
              Value: 22
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Connection Science
              Type: main
ResultId 1