Loading…
Exploring different attributes of source information for speaker verification with limited test data
This work explores mel power difference of spectrum in subband, residual mel frequency cepstral coefficient, and discrete cosine transform of the integrated linear prediction residual for speaker verification under limited test data conditions. These three source features are found to capture differ...
Saved in:
Published in: | The Journal of the Acoustical Society of America 2016-07, Vol.140 (1), p.184-190 |
---|---|
Main Authors: | , |
Format: | Article |
Language: | English |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c390t-204ad87462cf3c0da5d0c6113875e3b7297299b21741ee977de8e81bd75b22633 |
---|---|
cites | cdi_FETCH-LOGICAL-c390t-204ad87462cf3c0da5d0c6113875e3b7297299b21741ee977de8e81bd75b22633 |
container_end_page | 190 |
container_issue | 1 |
container_start_page | 184 |
container_title | The Journal of the Acoustical Society of America |
container_volume | 140 |
creator | Das, Rohan Kumar Mahadeva Prasanna, S. R. |
description | This work explores mel power difference of spectrum in subband, residual mel frequency cepstral coefficient, and discrete cosine transform of the integrated linear prediction residual for speaker verification under limited test data conditions. These three source features are found to capture different attributes of source information, namely, periodicity, smoothed spectrum information, and shape of the glottal signal, respectively. On the NIST SRE 2003 database, the proposed combination of the three source features performs better [equal error rate (EER): 20.19%, decision cost function (DCF): 0.3759] than the mel frequency cepstral coefficient feature (EER: 22.31%, DCF: 0.4128) for 2 s duration of test segments. |
doi_str_mv | 10.1121/1.4954653 |
format | article |
fullrecord | <record><control><sourceid>proquest_scita</sourceid><recordid>TN_cdi_scitation_primary_10_1121_1_4954653</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1808381974</sourcerecordid><originalsourceid>FETCH-LOGICAL-c390t-204ad87462cf3c0da5d0c6113875e3b7297299b21741ee977de8e81bd75b22633</originalsourceid><addsrcrecordid>eNp9kM1u1TAQRi0EopfCgheovASkFI9_YmeJqrZUqsQG1pFjj1tDEgfbaeHtCdwLXRXJ0ng0Z76RDiGvgZ0CcHgPp7JTslXiCdmB4qwxisunZMcYg0Z2bXtEXpTydWuVEd1zcsS11Aqk3BF__mMZU47zDfUxBMw4V2przXFYKxaaAi1pzQ5pnEPKk60xzXT70bKg_YaZ3mGOIbr94D7WWzrGKVb0dNuv1NtqX5JnwY4FXx3qMflycf757GNz_eny6uzDdeNEx2rDmbTeaNlyF4Rj3irPXAsgjFYoBs277XUDBy0BsdPao0EDg9dq4LwV4pi82ecuOX1ft-v9FIvDcbQzprX0YJgRBjotN_TtHnU5lZIx9EuOk80_e2D9b6k99AepG3tyiF2HCf0_8q_FDXi3B4qL9Y-I_6Y9Ct-l_AD2iw_iFxPijmU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1808381974</pqid></control><display><type>article</type><title>Exploring different attributes of source information for speaker verification with limited test data</title><source>American Institute of Physics:Jisc Collections:Transitional Journals Agreement 2021-23 (Reading list)</source><creator>Das, Rohan Kumar ; Mahadeva Prasanna, S. R.</creator><creatorcontrib>Das, Rohan Kumar ; Mahadeva Prasanna, S. R.</creatorcontrib><description>This work explores mel power difference of spectrum in subband, residual mel frequency cepstral coefficient, and discrete cosine transform of the integrated linear prediction residual for speaker verification under limited test data conditions. These three source features are found to capture different attributes of source information, namely, periodicity, smoothed spectrum information, and shape of the glottal signal, respectively. On the NIST SRE 2003 database, the proposed combination of the three source features performs better [equal error rate (EER): 20.19%, decision cost function (DCF): 0.3759] than the mel frequency cepstral coefficient feature (EER: 22.31%, DCF: 0.4128) for 2 s duration of test segments.</description><identifier>ISSN: 0001-4966</identifier><identifier>EISSN: 1520-8524</identifier><identifier>DOI: 10.1121/1.4954653</identifier><identifier>PMID: 27475144</identifier><identifier>CODEN: JASMAN</identifier><language>eng</language><publisher>United States</publisher><ispartof>The Journal of the Acoustical Society of America, 2016-07, Vol.140 (1), p.184-190</ispartof><rights>Acoustical Society of America</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c390t-204ad87462cf3c0da5d0c6113875e3b7297299b21741ee977de8e81bd75b22633</citedby><cites>FETCH-LOGICAL-c390t-204ad87462cf3c0da5d0c6113875e3b7297299b21741ee977de8e81bd75b22633</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27922,27923</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/27475144$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Das, Rohan Kumar</creatorcontrib><creatorcontrib>Mahadeva Prasanna, S. R.</creatorcontrib><title>Exploring different attributes of source information for speaker verification with limited test data</title><title>The Journal of the Acoustical Society of America</title><addtitle>J Acoust Soc Am</addtitle><description>This work explores mel power difference of spectrum in subband, residual mel frequency cepstral coefficient, and discrete cosine transform of the integrated linear prediction residual for speaker verification under limited test data conditions. These three source features are found to capture different attributes of source information, namely, periodicity, smoothed spectrum information, and shape of the glottal signal, respectively. On the NIST SRE 2003 database, the proposed combination of the three source features performs better [equal error rate (EER): 20.19%, decision cost function (DCF): 0.3759] than the mel frequency cepstral coefficient feature (EER: 22.31%, DCF: 0.4128) for 2 s duration of test segments.</description><issn>0001-4966</issn><issn>1520-8524</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><sourceid>AJDQP</sourceid><recordid>eNp9kM1u1TAQRi0EopfCgheovASkFI9_YmeJqrZUqsQG1pFjj1tDEgfbaeHtCdwLXRXJ0ng0Z76RDiGvgZ0CcHgPp7JTslXiCdmB4qwxisunZMcYg0Z2bXtEXpTydWuVEd1zcsS11Aqk3BF__mMZU47zDfUxBMw4V2przXFYKxaaAi1pzQ5pnEPKk60xzXT70bKg_YaZ3mGOIbr94D7WWzrGKVb0dNuv1NtqX5JnwY4FXx3qMflycf757GNz_eny6uzDdeNEx2rDmbTeaNlyF4Rj3irPXAsgjFYoBs277XUDBy0BsdPao0EDg9dq4LwV4pi82ecuOX1ft-v9FIvDcbQzprX0YJgRBjotN_TtHnU5lZIx9EuOk80_e2D9b6k99AepG3tyiF2HCf0_8q_FDXi3B4qL9Y-I_6Y9Ct-l_AD2iw_iFxPijmU</recordid><startdate>201607</startdate><enddate>201607</enddate><creator>Das, Rohan Kumar</creator><creator>Mahadeva Prasanna, S. R.</creator><scope>AJDQP</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>201607</creationdate><title>Exploring different attributes of source information for speaker verification with limited test data</title><author>Das, Rohan Kumar ; Mahadeva Prasanna, S. R.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c390t-204ad87462cf3c0da5d0c6113875e3b7297299b21741ee977de8e81bd75b22633</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Das, Rohan Kumar</creatorcontrib><creatorcontrib>Mahadeva Prasanna, S. R.</creatorcontrib><collection>AIP Open Access Journals</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>The Journal of the Acoustical Society of America</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Das, Rohan Kumar</au><au>Mahadeva Prasanna, S. R.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Exploring different attributes of source information for speaker verification with limited test data</atitle><jtitle>The Journal of the Acoustical Society of America</jtitle><addtitle>J Acoust Soc Am</addtitle><date>2016-07</date><risdate>2016</risdate><volume>140</volume><issue>1</issue><spage>184</spage><epage>190</epage><pages>184-190</pages><issn>0001-4966</issn><eissn>1520-8524</eissn><coden>JASMAN</coden><abstract>This work explores mel power difference of spectrum in subband, residual mel frequency cepstral coefficient, and discrete cosine transform of the integrated linear prediction residual for speaker verification under limited test data conditions. These three source features are found to capture different attributes of source information, namely, periodicity, smoothed spectrum information, and shape of the glottal signal, respectively. On the NIST SRE 2003 database, the proposed combination of the three source features performs better [equal error rate (EER): 20.19%, decision cost function (DCF): 0.3759] than the mel frequency cepstral coefficient feature (EER: 22.31%, DCF: 0.4128) for 2 s duration of test segments.</abstract><cop>United States</cop><pmid>27475144</pmid><doi>10.1121/1.4954653</doi><tpages>7</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0001-4966 |
ispartof | The Journal of the Acoustical Society of America, 2016-07, Vol.140 (1), p.184-190 |
issn | 0001-4966 1520-8524 |
language | eng |
recordid | cdi_scitation_primary_10_1121_1_4954653 |
source | American Institute of Physics:Jisc Collections:Transitional Journals Agreement 2021-23 (Reading list) |
title | Exploring different attributes of source information for speaker verification with limited test data |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T12%3A45%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_scita&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Exploring%20different%20attributes%20of%20source%20information%20for%20speaker%20verification%20with%20limited%20test%20data&rft.jtitle=The%20Journal%20of%20the%20Acoustical%20Society%20of%20America&rft.au=Das,%20Rohan%20Kumar&rft.date=2016-07&rft.volume=140&rft.issue=1&rft.spage=184&rft.epage=190&rft.pages=184-190&rft.issn=0001-4966&rft.eissn=1520-8524&rft.coden=JASMAN&rft_id=info:doi/10.1121/1.4954653&rft_dat=%3Cproquest_scita%3E1808381974%3C/proquest_scita%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c390t-204ad87462cf3c0da5d0c6113875e3b7297299b21741ee977de8e81bd75b22633%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1808381974&rft_id=info:pmid/27475144&rfr_iscdi=true |