Presentation	2005/1/17 How Children Learn to Segment Continuous Speech into Words? : A Neural Network Model of Lexical Segmentation Shogo MAKIOKA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	We constructed a neural network model of lexical segmentation. The model generates the representation of words by a novel self-organizing learning algorithm. The model compare the input phoneme sequences with its internal representation, and generates a new representation of the subsequence. We used child-oriented utterances in the CHILDES database as the training stimuli for the network. The performance of lexical segmentation was better than that of SRN. Furthermore, the model showed fairly good generalization ability.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Language Acquisition / Word Acquisition / Segmentation / Neural Network
Paper #	NC2004-124
Date of Issue

Conference Information
Committee	NC
Conference Date	2005/1/17(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)	How Children Learn to Segment Continuous Speech into Words? : A Neural Network Model of Lexical Segmentation
Sub Title (in English)
Keyword(1)	Language Acquisition
Keyword(2)	Word Acquisition
Keyword(3)	Segmentation
Keyword(4)	Neural Network
1st Author's Name	Shogo MAKIOKA
1st Author's Affiliation	Department of Human Sciences, Osaka Women's University()
Date	2005/1/17
Paper #	NC2004-124
Volume (vol)	vol.104
Number (no)	585
Page	pp.pp.-
#Pages	6
Date of Issue