A comparison Study of Cepstral Analysis with Applications to Speech Recognition

Three cepstral parametric methods were compared for speech recognition application: Real Cepstrum, Mel-Frequency Cepstrum and a new method Maximum Likelihood Cepstrum. The cepstral parameters were extracted from training and testing sets that, consisted of part of the TI-DIGIT database. The paramete...

Full description

Saved in:
Bibliographic Details
Main Authors: Zigelboim, G., Shallom, I.D.
Format: Conference Proceeding
Language:English
Subjects:
Additive noise
Cepstral analysis
Cepstrum
Engines
Hidden Markov models
Mel frequency cepstral coefficient
Parameter extraction
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 33
container_issue
container_start_page 30
container_title
container_volume
creator Zigelboim, G.
Shallom, I.D.
description Three cepstral parametric methods were compared for speech recognition application: Real Cepstrum, Mel-Frequency Cepstrum and a new method Maximum Likelihood Cepstrum. The cepstral parameters were extracted from training and testing sets that, consisted of part of the TI-DIGIT database. The parameter extraction (both stationary and dynamics) was performed by the HTK engine and Matlab scripts. Training and recognition were performed by HTK, using continues density HMMs. Simulations with additive noise were performed and their results compared. The maximum-likelihood cepstrum with dynamics has proved to be superior to the real cepstrum and significantly improved the recognition rate to be almost as high as of the Mel-frequency cepstrum.
doi_str_mv 10.1109/ITRE.2006.381527
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4266288</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4266288</ieee_id><sourcerecordid>4266288</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-78915459ca4927e0649569c495f14670c03690790490feb464fb75aec52bd0163</originalsourceid><addsrcrecordid>eNo1jF1LwzAYhSMiqLP3gjf5A51v0nxeljJ1MBhsE7wbaZa6SNeEJiL9907Uc3EeznNxELonMCcE9ONyt1nMKYCYV4pwKi9QoaUijDIGimt5iW7_h3q7RkVKH3BOpTmR7Aata2zDKZrRpzDgbf48TDh0uHEx5dH0uB5MPyWf8JfPR1zH2Htrsg9DwjngbXTOHvHG2fA--B99h6460ydX_HGGXp8Wu-alXK2fl029Kj2RPJdSacIZ19YwTaUDwTQX2p67I0xIsFAJDVID09C5lgnWtZIbZzltD0BENUMPv7_eObePoz-ZcdozKgRVqvoGic9OhQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A comparison Study of Cepstral Analysis with Applications to Speech Recognition</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Zigelboim, G. ; Shallom, I.D.</creator><creatorcontrib>Zigelboim, G. ; Shallom, I.D.</creatorcontrib><description>Three cepstral parametric methods were compared for speech recognition application: Real Cepstrum, Mel-Frequency Cepstrum and a new method Maximum Likelihood Cepstrum. The cepstral parameters were extracted from training and testing sets that, consisted of part of the TI-DIGIT database. The parameter extraction (both stationary and dynamics) was performed by the HTK engine and Matlab scripts. Training and recognition were performed by HTK, using continues density HMMs. Simulations with additive noise were performed and their results compared. The maximum-likelihood cepstrum with dynamics has proved to be superior to the real cepstrum and significantly improved the recognition rate to be almost as high as of the Mel-frequency cepstrum.</description><identifier>ISBN: 142440858X</identifier><identifier>ISBN: 9781424408580</identifier><identifier>EISBN: 9781424408597</identifier><identifier>EISBN: 1424408598</identifier><identifier>DOI: 10.1109/ITRE.2006.381527</identifier><language>eng</language><publisher>IEEE</publisher><subject>Additive noise ; Cepstral analysis ; Cepstrum ; Engines ; Hidden Markov models ; Mel frequency cepstral coefficient ; Parameter extraction ; Speech recognition ; Testing</subject><ispartof>2006 International Conference on Information Technology: Research and Education, 2006, p.30-33</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/4266288$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4266288$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Zigelboim, G.</creatorcontrib><creatorcontrib>Shallom, I.D.</creatorcontrib><title>A comparison Study of Cepstral Analysis with Applications to Speech Recognition</title><title>2006 International Conference on Information Technology: Research and Education</title><addtitle>ITRE</addtitle><description>Three cepstral parametric methods were compared for speech recognition application: Real Cepstrum, Mel-Frequency Cepstrum and a new method Maximum Likelihood Cepstrum. The cepstral parameters were extracted from training and testing sets that, consisted of part of the TI-DIGIT database. The parameter extraction (both stationary and dynamics) was performed by the HTK engine and Matlab scripts. Training and recognition were performed by HTK, using continues density HMMs. Simulations with additive noise were performed and their results compared. The maximum-likelihood cepstrum with dynamics has proved to be superior to the real cepstrum and significantly improved the recognition rate to be almost as high as of the Mel-frequency cepstrum.</description><subject>Additive noise</subject><subject>Cepstral analysis</subject><subject>Cepstrum</subject><subject>Engines</subject><subject>Hidden Markov models</subject><subject>Mel frequency cepstral coefficient</subject><subject>Parameter extraction</subject><subject>Speech recognition</subject><subject>Testing</subject><isbn>142440858X</isbn><isbn>9781424408580</isbn><isbn>9781424408597</isbn><isbn>1424408598</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2006</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1jF1LwzAYhSMiqLP3gjf5A51v0nxeljJ1MBhsE7wbaZa6SNeEJiL9907Uc3EeznNxELonMCcE9ONyt1nMKYCYV4pwKi9QoaUijDIGimt5iW7_h3q7RkVKH3BOpTmR7Aata2zDKZrRpzDgbf48TDh0uHEx5dH0uB5MPyWf8JfPR1zH2Htrsg9DwjngbXTOHvHG2fA--B99h6460ydX_HGGXp8Wu-alXK2fl029Kj2RPJdSacIZ19YwTaUDwTQX2p67I0xIsFAJDVID09C5lgnWtZIbZzltD0BENUMPv7_eObePoz-ZcdozKgRVqvoGic9OhQ</recordid><startdate>200610</startdate><enddate>200610</enddate><creator>Zigelboim, G.</creator><creator>Shallom, I.D.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200610</creationdate><title>A comparison Study of Cepstral Analysis with Applications to Speech Recognition</title><author>Zigelboim, G. ; Shallom, I.D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-78915459ca4927e0649569c495f14670c03690790490feb464fb75aec52bd0163</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Additive noise</topic><topic>Cepstral analysis</topic><topic>Cepstrum</topic><topic>Engines</topic><topic>Hidden Markov models</topic><topic>Mel frequency cepstral coefficient</topic><topic>Parameter extraction</topic><topic>Speech recognition</topic><topic>Testing</topic><toplevel>online_resources</toplevel><creatorcontrib>Zigelboim, G.</creatorcontrib><creatorcontrib>Shallom, I.D.</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</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>Zigelboim, G.</au><au>Shallom, I.D.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A comparison Study of Cepstral Analysis with Applications to Speech Recognition</atitle><btitle>2006 International Conference on Information Technology: Research and Education</btitle><stitle>ITRE</stitle><date>2006-10</date><risdate>2006</risdate><spage>30</spage><epage>33</epage><pages>30-33</pages><isbn>142440858X</isbn><isbn>9781424408580</isbn><eisbn>9781424408597</eisbn><eisbn>1424408598</eisbn><abstract>Three cepstral parametric methods were compared for speech recognition application: Real Cepstrum, Mel-Frequency Cepstrum and a new method Maximum Likelihood Cepstrum. The cepstral parameters were extracted from training and testing sets that, consisted of part of the TI-DIGIT database. The parameter extraction (both stationary and dynamics) was performed by the HTK engine and Matlab scripts. Training and recognition were performed by HTK, using continues density HMMs. Simulations with additive noise were performed and their results compared. The maximum-likelihood cepstrum with dynamics has proved to be superior to the real cepstrum and significantly improved the recognition rate to be almost as high as of the Mel-frequency cepstrum.</abstract><pub>IEEE</pub><doi>10.1109/ITRE.2006.381527</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 142440858X
ispartof 2006 International Conference on Information Technology: Research and Education, 2006, p.30-33
issn
language eng
recordid cdi_ieee_primary_4266288
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Additive noise
Cepstral analysis
Cepstrum
Engines
Hidden Markov models
Mel frequency cepstral coefficient
Parameter extraction
Speech recognition
Testing
title A comparison Study of Cepstral Analysis with Applications to Speech Recognition
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T10%3A47%3A59IST&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=A%20comparison%20Study%20of%20Cepstral%20Analysis%20with%20Applications%20to%20Speech%20Recognition&rft.btitle=2006%20International%20Conference%20on%20Information%20Technology:%20Research%20and%20Education&rft.au=Zigelboim,%20G.&rft.date=2006-10&rft.spage=30&rft.epage=33&rft.pages=30-33&rft.isbn=142440858X&rft.isbn_list=9781424408580&rft_id=info:doi/10.1109/ITRE.2006.381527&rft.eisbn=9781424408597&rft.eisbn_list=1424408598&rft_dat=%3Cieee_6IE%3E4266288%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-78915459ca4927e0649569c495f14670c03690790490feb464fb75aec52bd0163%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=4266288&rfr_iscdi=true