Presentation 2008-03-14
A study on a speech stream learning with statistical information
Miki HAYASAKA, Osamu WATANABE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is considered that the statistical property of speech streams plays an important role of language aquisition. Pena et at. reported that we could not acquire a grammatical-like structure from the statistical information. However, Pena's results could be interpreted by assuming subjects only learned the speech streams provided in their experiment with the statistical information. In this study, we investigate this hypothesis by using a comuputer simulation and an experiment. The result supports the possibility that Pena's data result from statistical learning of speech streams.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural network / Elman net / Statistical information / Language acquisition
Paper # NC2007-175
Date of Issue

Conference Information
Committee NC
Conference Date 2008/3/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study on a speech stream learning with statistical information
Sub Title (in English)
Keyword(1) Neural network
Keyword(2) Elman net
Keyword(3) Statistical information
Keyword(4) Language acquisition
1st Author's Name Miki HAYASAKA
1st Author's Affiliation Graduated school of Engineering, Muroran Institute of Technology()
2nd Author's Name Osamu WATANABE
2nd Author's Affiliation Faculty of Engineering, Muroran Institute of Technology
Date 2008-03-14
Paper # NC2007-175
Volume (vol) vol.107
Number (no) 542
Page pp.pp.-
#Pages 6
Date of Issue