Corrective training of hidden control neural network

A corrective training algorithm for hidden control neural network (HCNN) is proposed in this paper with application to the isolated spoken Korean digit recognition. The proposed algorithm tries to heuristically minimize the number of recognition errors, which improves the discriminatory power of the...

Full description

Saved in:
Bibliographic Details
Main Authors: KyungMin Na, Soo-Ik Chae, SouGuil Ann
Format: Conference Proceeding
Language:English
Subjects:
Artificial neural networks
Backpropagation algorithms
Electronic mail
Error correction
Hidden Markov models
Maximum likelihood estimation
Neural networks
Predictive models
Speech recognition
Testing
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 2870 vol.5
container_issue
container_start_page 2867
container_title
container_volume 5
creator KyungMin Na
Soo-Ik Chae
SouGuil Ann
description A corrective training algorithm for hidden control neural network (HCNN) is proposed in this paper with application to the isolated spoken Korean digit recognition. The proposed algorithm tries to heuristically minimize the number of recognition errors, which improves the discriminatory power of the conventional HCNN-based speech recognizers. Experimental results showed 25% reduction for closed test, and 10% reduction for open test in the number of recognition errors.
doi_str_mv 10.1109/ICNN.1995.488189
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_488189</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>488189</ieee_id><sourcerecordid>488189</sourcerecordid><originalsourceid>FETCH-LOGICAL-i104t-4bbb2bff9fc91fec219d275f0d5165ce2e4fdc72fb49dae6013634c2476850103</originalsourceid><addsrcrecordid>eNotj0tLxDAUhQMiKGP34qp_oDU3jyZ3KcXHwDBudD00yY1Gx1TSqvjvrcwcDny7j3MYuwTeAnC8XvfbbQuIulXWgsUTVqGxfKkUprN4xqppeuNLlNbS6HOm-rEU8nP6pnouQ8opv9RjrF9TCJRrP-a5jPs601cZ_jH_jOX9gp3GYT9RdeSKPd_dPvUPzebxft3fbJoEXM2Ncs4JFyNGjxDJC8AgjI48aOi0J0EqBm9EdArDQB0H2UnlhVqmag5crtjVwZuIaPdZ0sdQfneHa_IPvMdESw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Corrective training of hidden control neural network</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>KyungMin Na ; Soo-Ik Chae ; SouGuil Ann</creator><creatorcontrib>KyungMin Na ; Soo-Ik Chae ; SouGuil Ann</creatorcontrib><description>A corrective training algorithm for hidden control neural network (HCNN) is proposed in this paper with application to the isolated spoken Korean digit recognition. The proposed algorithm tries to heuristically minimize the number of recognition errors, which improves the discriminatory power of the conventional HCNN-based speech recognizers. Experimental results showed 25% reduction for closed test, and 10% reduction for open test in the number of recognition errors.</description><identifier>ISBN: 9780780327689</identifier><identifier>ISBN: 0780327683</identifier><identifier>DOI: 10.1109/ICNN.1995.488189</identifier><language>eng</language><publisher>IEEE</publisher><subject>Artificial neural networks ; Backpropagation algorithms ; Electronic mail ; Error correction ; Hidden Markov models ; Maximum likelihood estimation ; Neural networks ; Predictive models ; Speech recognition ; Testing</subject><ispartof>Proceedings of ICNN'95 - International Conference on Neural Networks, 1995, Vol.5, p.2867-2870 vol.5</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/488189$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,4036,4037,27904,54898</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/488189$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>KyungMin Na</creatorcontrib><creatorcontrib>Soo-Ik Chae</creatorcontrib><creatorcontrib>SouGuil Ann</creatorcontrib><title>Corrective training of hidden control neural network</title><title>Proceedings of ICNN'95 - International Conference on Neural Networks</title><addtitle>ICNN</addtitle><description>A corrective training algorithm for hidden control neural network (HCNN) is proposed in this paper with application to the isolated spoken Korean digit recognition. The proposed algorithm tries to heuristically minimize the number of recognition errors, which improves the discriminatory power of the conventional HCNN-based speech recognizers. Experimental results showed 25% reduction for closed test, and 10% reduction for open test in the number of recognition errors.</description><subject>Artificial neural networks</subject><subject>Backpropagation algorithms</subject><subject>Electronic mail</subject><subject>Error correction</subject><subject>Hidden Markov models</subject><subject>Maximum likelihood estimation</subject><subject>Neural networks</subject><subject>Predictive models</subject><subject>Speech recognition</subject><subject>Testing</subject><isbn>9780780327689</isbn><isbn>0780327683</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1995</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj0tLxDAUhQMiKGP34qp_oDU3jyZ3KcXHwDBudD00yY1Gx1TSqvjvrcwcDny7j3MYuwTeAnC8XvfbbQuIulXWgsUTVqGxfKkUprN4xqppeuNLlNbS6HOm-rEU8nP6pnouQ8opv9RjrF9TCJRrP-a5jPs601cZ_jH_jOX9gp3GYT9RdeSKPd_dPvUPzebxft3fbJoEXM2Ncs4JFyNGjxDJC8AgjI48aOi0J0EqBm9EdArDQB0H2UnlhVqmag5crtjVwZuIaPdZ0sdQfneHa_IPvMdESw</recordid><startdate>1995</startdate><enddate>1995</enddate><creator>KyungMin Na</creator><creator>Soo-Ik Chae</creator><creator>SouGuil Ann</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1995</creationdate><title>Corrective training of hidden control neural network</title><author>KyungMin Na ; Soo-Ik Chae ; SouGuil Ann</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i104t-4bbb2bff9fc91fec219d275f0d5165ce2e4fdc72fb49dae6013634c2476850103</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1995</creationdate><topic>Artificial neural networks</topic><topic>Backpropagation algorithms</topic><topic>Electronic mail</topic><topic>Error correction</topic><topic>Hidden Markov models</topic><topic>Maximum likelihood estimation</topic><topic>Neural networks</topic><topic>Predictive models</topic><topic>Speech recognition</topic><topic>Testing</topic><toplevel>online_resources</toplevel><creatorcontrib>KyungMin Na</creatorcontrib><creatorcontrib>Soo-Ik Chae</creatorcontrib><creatorcontrib>SouGuil Ann</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KyungMin Na</au><au>Soo-Ik Chae</au><au>SouGuil Ann</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Corrective training of hidden control neural network</atitle><btitle>Proceedings of ICNN'95 - International Conference on Neural Networks</btitle><stitle>ICNN</stitle><date>1995</date><risdate>1995</risdate><volume>5</volume><spage>2867</spage><epage>2870 vol.5</epage><pages>2867-2870 vol.5</pages><isbn>9780780327689</isbn><isbn>0780327683</isbn><abstract>A corrective training algorithm for hidden control neural network (HCNN) is proposed in this paper with application to the isolated spoken Korean digit recognition. The proposed algorithm tries to heuristically minimize the number of recognition errors, which improves the discriminatory power of the conventional HCNN-based speech recognizers. Experimental results showed 25% reduction for closed test, and 10% reduction for open test in the number of recognition errors.</abstract><pub>IEEE</pub><doi>10.1109/ICNN.1995.488189</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9780780327689
ispartof Proceedings of ICNN'95 - International Conference on Neural Networks, 1995, Vol.5, p.2867-2870 vol.5
issn
language eng
recordid cdi_ieee_primary_488189
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Artificial neural networks
Backpropagation algorithms
Electronic mail
Error correction
Hidden Markov models
Maximum likelihood estimation
Neural networks
Predictive models
Speech recognition
Testing
title Corrective training of hidden control neural network
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T04%3A29%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Corrective%20training%20of%20hidden%20control%20neural%20network&rft.btitle=Proceedings%20of%20ICNN'95%20-%20International%20Conference%20on%20Neural%20Networks&rft.au=KyungMin%20Na&rft.date=1995&rft.volume=5&rft.spage=2867&rft.epage=2870%20vol.5&rft.pages=2867-2870%20vol.5&rft.isbn=9780780327689&rft.isbn_list=0780327683&rft_id=info:doi/10.1109/ICNN.1995.488189&rft_dat=%3Cieee_6IE%3E488189%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i104t-4bbb2bff9fc91fec219d275f0d5165ce2e4fdc72fb49dae6013634c2476850103%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=488189&rfr_iscdi=true