An Efficient Feature Selection Method for Speaker Recognition
In this paper, a new feature selection method for speaker recognition is proposed to keep the high quality speech frames for speaker modelling and to remove noisy and corrupted speech frames. In order to obtain robust voice activity detection in variety of acoustic conditions, the spectral subtracti...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 4 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Hanwu Sun Bin Ma Haizhou Li |
| description | In this paper, a new feature selection method for speaker recognition is proposed to keep the high quality speech frames for speaker modelling and to remove noisy and corrupted speech frames. In order to obtain robust voice activity detection in variety of acoustic conditions, the spectral subtraction algorithm is adopted to estimate the frame power. An energy based frame selection algorithm is then applied to indicate the speech activity at the frame level. The eigenchannel based GMM-UBM speaker recognition system is used to evaluate this proposed method. The experiments are conducted on the 2006 NIST Speaker Recognition Evaluation core test condition (telephone channel) as well as microphone channel test condition. It demonstrates that this approach can provide an efficient way to select high quality speech frames in the noisy environment for speaker recognition. |
| doi_str_mv | 10.1109/CHINSL.2008.ECP.57 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4730311</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4730311</ieee_id><sourcerecordid>4730311</sourcerecordid><originalsourceid>FETCH-LOGICAL-i1347-cd17742a9a60de8319da1c57cd84684fd9fb552240fcc2d96a59e4148f398b163</originalsourceid><addsrcrecordid>eNpVjMtOwzAURI1QJaD0B2DjH2jwta9je8GiilJaqTxEYF259jUYSlKlYcHfQwUbZjM6mqNh7AJEASDcVbVY3jWrQgphi7p6KLQ5YhNnLKBElA4VHP9jiSN2drCdsCXCCZvs92_iJ6iVEXjKrmctr1PKIVM78Dn54bMn3tCWwpC7lt_S8NpFnrqeNzvy79TzRwrdS5sP8zkbJb_d0-Svx-x5Xj9Vi-nq_mZZzVbTDArNNEQwBqV3vhSRrAIXPQRtQrRYWkzRpY3WUqJIIcjoSq8dIaBNytkNlGrMLn9_MxGtd33-8P3XGo0SCkB9A--5S7I</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>An Efficient Feature Selection Method for Speaker Recognition</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Hanwu Sun ; Bin Ma ; Haizhou Li</creator><creatorcontrib>Hanwu Sun ; Bin Ma ; Haizhou Li</creatorcontrib><description>In this paper, a new feature selection method for speaker recognition is proposed to keep the high quality speech frames for speaker modelling and to remove noisy and corrupted speech frames. In order to obtain robust voice activity detection in variety of acoustic conditions, the spectral subtraction algorithm is adopted to estimate the frame power. An energy based frame selection algorithm is then applied to indicate the speech activity at the frame level. The eigenchannel based GMM-UBM speaker recognition system is used to evaluate this proposed method. The experiments are conducted on the 2006 NIST Speaker Recognition Evaluation core test condition (telephone channel) as well as microphone channel test condition. It demonstrates that this approach can provide an efficient way to select high quality speech frames in the noisy environment for speaker recognition.</description><identifier>ISBN: 9781424429424</identifier><identifier>ISBN: 1424429420</identifier><identifier>EISBN: 9781424429431</identifier><identifier>EISBN: 1424429439</identifier><identifier>DOI: 10.1109/CHINSL.2008.ECP.57</identifier><identifier>LCCN: 2008908641</identifier><language>eng</language><publisher>IEEE</publisher><subject>Acoustic noise ; Acoustic signal detection ; Loudspeakers ; Microphones ; NIST ; Robustness ; Speaker recognition ; Speech ; Telephony ; Testing</subject><ispartof>2008 6th International Symposium on Chinese Spoken Language Processing, 2008, p.1-4</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4730311$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4730311$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Hanwu Sun</creatorcontrib><creatorcontrib>Bin Ma</creatorcontrib><creatorcontrib>Haizhou Li</creatorcontrib><title>An Efficient Feature Selection Method for Speaker Recognition</title><title>2008 6th International Symposium on Chinese Spoken Language Processing</title><addtitle>CHINSL</addtitle><description>In this paper, a new feature selection method for speaker recognition is proposed to keep the high quality speech frames for speaker modelling and to remove noisy and corrupted speech frames. In order to obtain robust voice activity detection in variety of acoustic conditions, the spectral subtraction algorithm is adopted to estimate the frame power. An energy based frame selection algorithm is then applied to indicate the speech activity at the frame level. The eigenchannel based GMM-UBM speaker recognition system is used to evaluate this proposed method. The experiments are conducted on the 2006 NIST Speaker Recognition Evaluation core test condition (telephone channel) as well as microphone channel test condition. It demonstrates that this approach can provide an efficient way to select high quality speech frames in the noisy environment for speaker recognition.</description><subject>Acoustic noise</subject><subject>Acoustic signal detection</subject><subject>Loudspeakers</subject><subject>Microphones</subject><subject>NIST</subject><subject>Robustness</subject><subject>Speaker recognition</subject><subject>Speech</subject><subject>Telephony</subject><subject>Testing</subject><isbn>9781424429424</isbn><isbn>1424429420</isbn><isbn>9781424429431</isbn><isbn>1424429439</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVjMtOwzAURI1QJaD0B2DjH2jwta9je8GiilJaqTxEYF259jUYSlKlYcHfQwUbZjM6mqNh7AJEASDcVbVY3jWrQgphi7p6KLQ5YhNnLKBElA4VHP9jiSN2drCdsCXCCZvs92_iJ6iVEXjKrmctr1PKIVM78Dn54bMn3tCWwpC7lt_S8NpFnrqeNzvy79TzRwrdS5sP8zkbJb_d0-Svx-x5Xj9Vi-nq_mZZzVbTDArNNEQwBqV3vhSRrAIXPQRtQrRYWkzRpY3WUqJIIcjoSq8dIaBNytkNlGrMLn9_MxGtd33-8P3XGo0SCkB9A--5S7I</recordid><startdate>200812</startdate><enddate>200812</enddate><creator>Hanwu Sun</creator><creator>Bin Ma</creator><creator>Haizhou Li</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200812</creationdate><title>An Efficient Feature Selection Method for Speaker Recognition</title><author>Hanwu Sun ; Bin Ma ; Haizhou Li</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i1347-cd17742a9a60de8319da1c57cd84684fd9fb552240fcc2d96a59e4148f398b163</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Acoustic noise</topic><topic>Acoustic signal detection</topic><topic>Loudspeakers</topic><topic>Microphones</topic><topic>NIST</topic><topic>Robustness</topic><topic>Speaker recognition</topic><topic>Speech</topic><topic>Telephony</topic><topic>Testing</topic><toplevel>online_resources</toplevel><creatorcontrib>Hanwu Sun</creatorcontrib><creatorcontrib>Bin Ma</creatorcontrib><creatorcontrib>Haizhou Li</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 Electronic Library (IEL)</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>Hanwu Sun</au><au>Bin Ma</au><au>Haizhou Li</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>An Efficient Feature Selection Method for Speaker Recognition</atitle><btitle>2008 6th International Symposium on Chinese Spoken Language Processing</btitle><stitle>CHINSL</stitle><date>2008-12</date><risdate>2008</risdate><spage>1</spage><epage>4</epage><pages>1-4</pages><isbn>9781424429424</isbn><isbn>1424429420</isbn><eisbn>9781424429431</eisbn><eisbn>1424429439</eisbn><abstract>In this paper, a new feature selection method for speaker recognition is proposed to keep the high quality speech frames for speaker modelling and to remove noisy and corrupted speech frames. In order to obtain robust voice activity detection in variety of acoustic conditions, the spectral subtraction algorithm is adopted to estimate the frame power. An energy based frame selection algorithm is then applied to indicate the speech activity at the frame level. The eigenchannel based GMM-UBM speaker recognition system is used to evaluate this proposed method. The experiments are conducted on the 2006 NIST Speaker Recognition Evaluation core test condition (telephone channel) as well as microphone channel test condition. It demonstrates that this approach can provide an efficient way to select high quality speech frames in the noisy environment for speaker recognition.</abstract><pub>IEEE</pub><doi>10.1109/CHINSL.2008.ECP.57</doi><tpages>4</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 9781424429424 |
| ispartof | 2008 6th International Symposium on Chinese Spoken Language Processing, 2008, p.1-4 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_4730311 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Acoustic noise Acoustic signal detection Loudspeakers Microphones NIST Robustness Speaker recognition Speech Telephony Testing |
| title | An Efficient Feature Selection Method for Speaker Recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T11%3A56%3A08IST&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=An%20Efficient%20Feature%20Selection%20Method%20for%20Speaker%20Recognition&rft.btitle=2008%206th%20International%20Symposium%20on%20Chinese%20Spoken%20Language%20Processing&rft.au=Hanwu%20Sun&rft.date=2008-12&rft.spage=1&rft.epage=4&rft.pages=1-4&rft.isbn=9781424429424&rft.isbn_list=1424429420&rft_id=info:doi/10.1109/CHINSL.2008.ECP.57&rft_dat=%3Cieee_6IE%3E4730311%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424429431&rft.eisbn_list=1424429439&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4730311&rfr_iscdi=true |