Towards language independent acoustic modeling

We describe procedures and experimental results using speech from diverse source languages to build an ASR system for a single target language. This work is intended to improve ASR in languages for which large amounts of training data are not available. We have developed both knowledge-based and aut...

Full description

Saved in:
Bibliographic Details
Main Authors: Byrne, W., Beyerlein, P., Huerta, J.M., Khudanpur, S., Marthi, B., Morgan, J., Peterek, N., Picone, J., Vergyri, D., Wang, T.
Format: Conference Proceeding
Language:English
Subjects:
Acoustical engineering
Asia
Automatic speech recognition
Europe
Hidden Markov models
Loudspeakers
Natural languages
Speech recognition
Statistical analysis
Training data
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c221t-60f8ef80dd3eec8da1cda3cdd9dbdba2a6bb89286dc7394c5534c3741eb9878b3
cites
container_end_page II1032 vol.2
container_issue
container_start_page II1029
container_title
container_volume 2
creator Byrne, W.
Beyerlein, P.
Huerta, J.M.
Khudanpur, S.
Marthi, B.
Morgan, J.
Peterek, N.
Picone, J.
Vergyri, D.
Wang, T.
description We describe procedures and experimental results using speech from diverse source languages to build an ASR system for a single target language. This work is intended to improve ASR in languages for which large amounts of training data are not available. We have developed both knowledge-based and automatic methods to map phonetic units from the source languages to the target language. We employed HMM adaptation techniques and discriminative model combination to combine acoustic models from the individual source languages for recognition of speech in the target language. Experiments are described in which Czech Broadcast News is transcribed using acoustic models trained from small amounts of Czech read speech augmented by English, Spanish, Russian, and Mandarin acoustic models.
doi_str_mv 10.1109/ICASSP.2000.859138
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_859138</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>859138</ieee_id><sourcerecordid>859138</sourcerecordid><originalsourceid>FETCH-LOGICAL-c221t-60f8ef80dd3eec8da1cda3cdd9dbdba2a6bb89286dc7394c5534c3741eb9878b3</originalsourceid><addsrcrecordid>eNotj91Kw0AUhBd_wFj7Ar3KCyTuT5I951KKWqGg0Areld09JyGSJiWbIr69gQrDzNU3zAixUjJXSuLj2_ppt_vItZQyhxKVgSuRaGMxUyi_rsUSLchZptJo9I1IVKllVqkC78R9jN8zB7aAROT74ceNFNPO9c3ZNZy2PfGJZ-un1IXhHKc2pMeBuGv75kHc1q6LvPzPhfh8ed6vN9n2_XXetM2C1mrKKlkD1yCJDHMAciqQM4EIyZN32lXeA2qoKFiDRShLUwRjC8UewYI3C7G69LbMfDiN7dGNv4fLU_MH41ZG0w</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Towards language independent acoustic modeling</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Byrne, W. ; Beyerlein, P. ; Huerta, J.M. ; Khudanpur, S. ; Marthi, B. ; Morgan, J. ; Peterek, N. ; Picone, J. ; Vergyri, D. ; Wang, T.</creator><creatorcontrib>Byrne, W. ; Beyerlein, P. ; Huerta, J.M. ; Khudanpur, S. ; Marthi, B. ; Morgan, J. ; Peterek, N. ; Picone, J. ; Vergyri, D. ; Wang, T.</creatorcontrib><description>We describe procedures and experimental results using speech from diverse source languages to build an ASR system for a single target language. This work is intended to improve ASR in languages for which large amounts of training data are not available. We have developed both knowledge-based and automatic methods to map phonetic units from the source languages to the target language. We employed HMM adaptation techniques and discriminative model combination to combine acoustic models from the individual source languages for recognition of speech in the target language. Experiments are described in which Czech Broadcast News is transcribed using acoustic models trained from small amounts of Czech read speech augmented by English, Spanish, Russian, and Mandarin acoustic models.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9780780362932</identifier><identifier>ISBN: 0780362934</identifier><identifier>EISSN: 2379-190X</identifier><identifier>DOI: 10.1109/ICASSP.2000.859138</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustical engineering ; Asia ; Automatic speech recognition ; Europe ; Hidden Markov models ; Loudspeakers ; Natural languages ; Speech recognition ; Statistical analysis ; Training data</subject><ispartof>2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100), 2000, Vol.2, p.II1029-II1032 vol.2</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c221t-60f8ef80dd3eec8da1cda3cdd9dbdba2a6bb89286dc7394c5534c3741eb9878b3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/859138$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,4050,4051,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/859138$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Byrne, W.</creatorcontrib><creatorcontrib>Beyerlein, P.</creatorcontrib><creatorcontrib>Huerta, J.M.</creatorcontrib><creatorcontrib>Khudanpur, S.</creatorcontrib><creatorcontrib>Marthi, B.</creatorcontrib><creatorcontrib>Morgan, J.</creatorcontrib><creatorcontrib>Peterek, N.</creatorcontrib><creatorcontrib>Picone, J.</creatorcontrib><creatorcontrib>Vergyri, D.</creatorcontrib><creatorcontrib>Wang, T.</creatorcontrib><title>Towards language independent acoustic modeling</title><title>2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)</title><addtitle>ICASSP</addtitle><description>We describe procedures and experimental results using speech from diverse source languages to build an ASR system for a single target language. This work is intended to improve ASR in languages for which large amounts of training data are not available. We have developed both knowledge-based and automatic methods to map phonetic units from the source languages to the target language. We employed HMM adaptation techniques and discriminative model combination to combine acoustic models from the individual source languages for recognition of speech in the target language. Experiments are described in which Czech Broadcast News is transcribed using acoustic models trained from small amounts of Czech read speech augmented by English, Spanish, Russian, and Mandarin acoustic models.</description><subject>Acoustical engineering</subject><subject>Asia</subject><subject>Automatic speech recognition</subject><subject>Europe</subject><subject>Hidden Markov models</subject><subject>Loudspeakers</subject><subject>Natural languages</subject><subject>Speech recognition</subject><subject>Statistical analysis</subject><subject>Training data</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9780780362932</isbn><isbn>0780362934</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2000</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj91Kw0AUhBd_wFj7Ar3KCyTuT5I951KKWqGg0Areld09JyGSJiWbIr69gQrDzNU3zAixUjJXSuLj2_ppt_vItZQyhxKVgSuRaGMxUyi_rsUSLchZptJo9I1IVKllVqkC78R9jN8zB7aAROT74ceNFNPO9c3ZNZy2PfGJZ-un1IXhHKc2pMeBuGv75kHc1q6LvPzPhfh8ed6vN9n2_XXetM2C1mrKKlkD1yCJDHMAciqQM4EIyZN32lXeA2qoKFiDRShLUwRjC8UewYI3C7G69LbMfDiN7dGNv4fLU_MH41ZG0w</recordid><startdate>2000</startdate><enddate>2000</enddate><creator>Byrne, W.</creator><creator>Beyerlein, P.</creator><creator>Huerta, J.M.</creator><creator>Khudanpur, S.</creator><creator>Marthi, B.</creator><creator>Morgan, J.</creator><creator>Peterek, N.</creator><creator>Picone, J.</creator><creator>Vergyri, D.</creator><creator>Wang, T.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>2000</creationdate><title>Towards language independent acoustic modeling</title><author>Byrne, W. ; Beyerlein, P. ; Huerta, J.M. ; Khudanpur, S. ; Marthi, B. ; Morgan, J. ; Peterek, N. ; Picone, J. ; Vergyri, D. ; Wang, T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c221t-60f8ef80dd3eec8da1cda3cdd9dbdba2a6bb89286dc7394c5534c3741eb9878b3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2000</creationdate><topic>Acoustical engineering</topic><topic>Asia</topic><topic>Automatic speech recognition</topic><topic>Europe</topic><topic>Hidden Markov models</topic><topic>Loudspeakers</topic><topic>Natural languages</topic><topic>Speech recognition</topic><topic>Statistical analysis</topic><topic>Training data</topic><toplevel>online_resources</toplevel><creatorcontrib>Byrne, W.</creatorcontrib><creatorcontrib>Beyerlein, P.</creatorcontrib><creatorcontrib>Huerta, J.M.</creatorcontrib><creatorcontrib>Khudanpur, S.</creatorcontrib><creatorcontrib>Marthi, B.</creatorcontrib><creatorcontrib>Morgan, J.</creatorcontrib><creatorcontrib>Peterek, N.</creatorcontrib><creatorcontrib>Picone, J.</creatorcontrib><creatorcontrib>Vergyri, D.</creatorcontrib><creatorcontrib>Wang, T.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Byrne, W.</au><au>Beyerlein, P.</au><au>Huerta, J.M.</au><au>Khudanpur, S.</au><au>Marthi, B.</au><au>Morgan, J.</au><au>Peterek, N.</au><au>Picone, J.</au><au>Vergyri, D.</au><au>Wang, T.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Towards language independent acoustic modeling</atitle><btitle>2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)</btitle><stitle>ICASSP</stitle><date>2000</date><risdate>2000</risdate><volume>2</volume><spage>II1029</spage><epage>II1032 vol.2</epage><pages>II1029-II1032 vol.2</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9780780362932</isbn><isbn>0780362934</isbn><abstract>We describe procedures and experimental results using speech from diverse source languages to build an ASR system for a single target language. This work is intended to improve ASR in languages for which large amounts of training data are not available. We have developed both knowledge-based and automatic methods to map phonetic units from the source languages to the target language. We employed HMM adaptation techniques and discriminative model combination to combine acoustic models from the individual source languages for recognition of speech in the target language. Experiments are described in which Czech Broadcast News is transcribed using acoustic models trained from small amounts of Czech read speech augmented by English, Spanish, Russian, and Mandarin acoustic models.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2000.859138</doi></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1520-6149
ispartof 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100), 2000, Vol.2, p.II1029-II1032 vol.2
issn 1520-6149
2379-190X
language eng
recordid cdi_ieee_primary_859138
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Acoustical engineering
Asia
Automatic speech recognition
Europe
Hidden Markov models
Loudspeakers
Natural languages
Speech recognition
Statistical analysis
Training data
title Towards language independent acoustic modeling
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T04%3A11%3A44IST&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=Towards%20language%20independent%20acoustic%20modeling&rft.btitle=2000%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech,%20and%20Signal%20Processing.%20Proceedings%20(Cat.%20No.00CH37100)&rft.au=Byrne,%20W.&rft.date=2000&rft.volume=2&rft.spage=II1029&rft.epage=II1032%20vol.2&rft.pages=II1029-II1032%20vol.2&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9780780362932&rft.isbn_list=0780362934&rft_id=info:doi/10.1109/ICASSP.2000.859138&rft_dat=%3Cieee_6IE%3E859138%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c221t-60f8ef80dd3eec8da1cda3cdd9dbdba2a6bb89286dc7394c5534c3741eb9878b3%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=859138&rfr_iscdi=true