Modeling spoken language acquisition with a generic cognitive architecture for associative learning

Okko Räsänen, Heikki Rasilo, Unto Laine

Research output: Chapter in Book/Report/Conference proceedingConference paper

1 Citation (Scopus)

Abstract

Human neo-cortex can be viewed as a modality invariant system for pattern discovery and associative learning. Similarly, research in the field of distributional learning suggests that much of human language acquisition can be explained by generic statistical learning mechanisms. The current paper argues that pattern processing capabilities of the human brain can be better understood if the process of early language acquisition is modeled using an entire cognitive architecture capable of unsupervised pattern discovery and associative learning. A high- level motivation and description for generic processing principles in such architecture are given, followed by examples of our current work in the field.
Original languageEnglish
Title of host publication13th Annual Conference of the International Speech Communication Association 2012 (INTERSPEECH 2012)
Subtitle of host publicationProceedings of a meeting held 9-13 September 2012, Portland, Oregon, USA.
Place of PublicationPortland (OR)
PublisherISCA
Pages918-921
Number of pages4
Volume2
ISBN (Print)9781622767595
Publication statusPublished - 9 Sep 2012
Event13th Annual Conference of the International Speech Communication Association 2012 (INTERSPEECH 2012) - Portland, United States
Duration: 9 Sep 201213 Sep 2012

Conference

Conference13th Annual Conference of the International Speech Communication Association 2012 (INTERSPEECH 2012)
Abbreviated titleInterspeech 2012
CountryUnited States
CityPortland
Period9/09/1213/09/12

Keywords

  • language acquisition
  • computational modeling
  • statistical learning
  • associative learning
  • multimodality
  • memory architectures

Fingerprint

Dive into the research topics of 'Modeling spoken language acquisition with a generic cognitive architecture for associative learning'. Together they form a unique fingerprint.

Cite this