Speech enhancement using an Improved MMSE estimator with Laplacian prior
In this paper we present an optimal estimator of magnitude spectrum for speech enhancement when the clean speech DFT coefficients are modeled by a Laplacian distribution and the noise DFT coefficients are modeled by a Gaussian distribution. Chen has already introduced a Minimum Mean Square Error (MM...
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 | 894 |
|---|---|
| container_issue | |
| container_start_page | 889 |
| container_title | |
| container_volume | |
| creator | Rashidi-nejad, M Abutalebi, H R Tadaion, A A |
| description | In this paper we present an optimal estimator of magnitude spectrum for speech enhancement when the clean speech DFT coefficients are modeled by a Laplacian distribution and the noise DFT coefficients are modeled by a Gaussian distribution. Chen has already introduced a Minimum Mean Square Error (MMSE) estimator of the magnitude spectrum. However, the proposed estimator, namely LapMMSE, does not have a closed form and is computationally extensive. We use his formulation for the MMSE estimator, employ some approximations and propose a computationally effective estimator for the magnitude spectrum. Experimental studies demonstrate better performance of our proposed estimator, Improved LapMMSE (ImpLapMMSE) Compared to LapMMSE and previous estimators in which Laplacian and Gaussian assumptions were made. |
| doi_str_mv | 10.1109/ISTEL.2010.5734148 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5734148</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5734148</ieee_id><sourcerecordid>5734148</sourcerecordid><originalsourceid>FETCH-LOGICAL-i1348-8910d6ad58a9fd47b4592cc6b48f2611996e7c49cd7ec02410f5eda3be804d33</originalsourceid><addsrcrecordid>eNpFj09LxDAUxCMiqOt-Ab3kC3TNS17b5ChLdRe6eGgP3pY0ebWR7R_aqvjtLbjgXIYfDDMMY_cgNgDCPO6LMss3UiwcpwoB9QW7BZSIGjTqy39Qb9dsPU0fYlEs0xj0DdsVA5FrOHWN7Ry11M38cwrdO7cd37fD2H-R54dDkXGa5tDauR_5d5gbntvhZF1YYsMY-vGOXdX2NNH67CtWPmfldhflry_77VMeBVCoI21A-MT6WFtTe0wrjI10LqlQ1zIBMCah1KFxPiUnJIKoY_JWVaQFeqVW7OGvNhDRcVlu7fhzPB9Xv7tETG8</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Speech enhancement using an Improved MMSE estimator with Laplacian prior</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Rashidi-nejad, M ; Abutalebi, H R ; Tadaion, A A</creator><creatorcontrib>Rashidi-nejad, M ; Abutalebi, H R ; Tadaion, A A</creatorcontrib><description>In this paper we present an optimal estimator of magnitude spectrum for speech enhancement when the clean speech DFT coefficients are modeled by a Laplacian distribution and the noise DFT coefficients are modeled by a Gaussian distribution. Chen has already introduced a Minimum Mean Square Error (MMSE) estimator of the magnitude spectrum. However, the proposed estimator, namely LapMMSE, does not have a closed form and is computationally extensive. We use his formulation for the MMSE estimator, employ some approximations and propose a computationally effective estimator for the magnitude spectrum. Experimental studies demonstrate better performance of our proposed estimator, Improved LapMMSE (ImpLapMMSE) Compared to LapMMSE and previous estimators in which Laplacian and Gaussian assumptions were made.</description><identifier>ISBN: 142448183X</identifier><identifier>ISBN: 9781424481835</identifier><identifier>EISBN: 1424481848</identifier><identifier>EISBN: 9781424481842</identifier><identifier>DOI: 10.1109/ISTEL.2010.5734148</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational modeling ; Discrete Fourier transforms ; Function approximation ; ImpLapMMSE ; Laplace equations ; Laplacian speech modeling ; MMSE estimator ; Speech ; Speech enhancement</subject><ispartof>2010 5th International Symposium on Telecommunications, 2010, p.889-894</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/5734148$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,27906,54901</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5734148$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Rashidi-nejad, M</creatorcontrib><creatorcontrib>Abutalebi, H R</creatorcontrib><creatorcontrib>Tadaion, A A</creatorcontrib><title>Speech enhancement using an Improved MMSE estimator with Laplacian prior</title><title>2010 5th International Symposium on Telecommunications</title><addtitle>ISTEL</addtitle><description>In this paper we present an optimal estimator of magnitude spectrum for speech enhancement when the clean speech DFT coefficients are modeled by a Laplacian distribution and the noise DFT coefficients are modeled by a Gaussian distribution. Chen has already introduced a Minimum Mean Square Error (MMSE) estimator of the magnitude spectrum. However, the proposed estimator, namely LapMMSE, does not have a closed form and is computationally extensive. We use his formulation for the MMSE estimator, employ some approximations and propose a computationally effective estimator for the magnitude spectrum. Experimental studies demonstrate better performance of our proposed estimator, Improved LapMMSE (ImpLapMMSE) Compared to LapMMSE and previous estimators in which Laplacian and Gaussian assumptions were made.</description><subject>Computational modeling</subject><subject>Discrete Fourier transforms</subject><subject>Function approximation</subject><subject>ImpLapMMSE</subject><subject>Laplace equations</subject><subject>Laplacian speech modeling</subject><subject>MMSE estimator</subject><subject>Speech</subject><subject>Speech enhancement</subject><isbn>142448183X</isbn><isbn>9781424481835</isbn><isbn>1424481848</isbn><isbn>9781424481842</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpFj09LxDAUxCMiqOt-Ab3kC3TNS17b5ChLdRe6eGgP3pY0ebWR7R_aqvjtLbjgXIYfDDMMY_cgNgDCPO6LMss3UiwcpwoB9QW7BZSIGjTqy39Qb9dsPU0fYlEs0xj0DdsVA5FrOHWN7Ry11M38cwrdO7cd37fD2H-R54dDkXGa5tDauR_5d5gbntvhZF1YYsMY-vGOXdX2NNH67CtWPmfldhflry_77VMeBVCoI21A-MT6WFtTe0wrjI10LqlQ1zIBMCah1KFxPiUnJIKoY_JWVaQFeqVW7OGvNhDRcVlu7fhzPB9Xv7tETG8</recordid><startdate>201012</startdate><enddate>201012</enddate><creator>Rashidi-nejad, M</creator><creator>Abutalebi, H R</creator><creator>Tadaion, A A</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201012</creationdate><title>Speech enhancement using an Improved MMSE estimator with Laplacian prior</title><author>Rashidi-nejad, M ; Abutalebi, H R ; Tadaion, A A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i1348-8910d6ad58a9fd47b4592cc6b48f2611996e7c49cd7ec02410f5eda3be804d33</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Computational modeling</topic><topic>Discrete Fourier transforms</topic><topic>Function approximation</topic><topic>ImpLapMMSE</topic><topic>Laplace equations</topic><topic>Laplacian speech modeling</topic><topic>MMSE estimator</topic><topic>Speech</topic><topic>Speech enhancement</topic><toplevel>online_resources</toplevel><creatorcontrib>Rashidi-nejad, M</creatorcontrib><creatorcontrib>Abutalebi, H R</creatorcontrib><creatorcontrib>Tadaion, A A</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>Rashidi-nejad, M</au><au>Abutalebi, H R</au><au>Tadaion, A A</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Speech enhancement using an Improved MMSE estimator with Laplacian prior</atitle><btitle>2010 5th International Symposium on Telecommunications</btitle><stitle>ISTEL</stitle><date>2010-12</date><risdate>2010</risdate><spage>889</spage><epage>894</epage><pages>889-894</pages><isbn>142448183X</isbn><isbn>9781424481835</isbn><eisbn>1424481848</eisbn><eisbn>9781424481842</eisbn><abstract>In this paper we present an optimal estimator of magnitude spectrum for speech enhancement when the clean speech DFT coefficients are modeled by a Laplacian distribution and the noise DFT coefficients are modeled by a Gaussian distribution. Chen has already introduced a Minimum Mean Square Error (MMSE) estimator of the magnitude spectrum. However, the proposed estimator, namely LapMMSE, does not have a closed form and is computationally extensive. We use his formulation for the MMSE estimator, employ some approximations and propose a computationally effective estimator for the magnitude spectrum. Experimental studies demonstrate better performance of our proposed estimator, Improved LapMMSE (ImpLapMMSE) Compared to LapMMSE and previous estimators in which Laplacian and Gaussian assumptions were made.</abstract><pub>IEEE</pub><doi>10.1109/ISTEL.2010.5734148</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 142448183X |
| ispartof | 2010 5th International Symposium on Telecommunications, 2010, p.889-894 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_5734148 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Computational modeling Discrete Fourier transforms Function approximation ImpLapMMSE Laplace equations Laplacian speech modeling MMSE estimator Speech Speech enhancement |
| title | Speech enhancement using an Improved MMSE estimator with Laplacian prior |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-20T05%3A02%3A23IST&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=Speech%20enhancement%20using%20an%20Improved%20MMSE%20estimator%20with%20Laplacian%20prior&rft.btitle=2010%205th%20International%20Symposium%20on%20Telecommunications&rft.au=Rashidi-nejad,%20M&rft.date=2010-12&rft.spage=889&rft.epage=894&rft.pages=889-894&rft.isbn=142448183X&rft.isbn_list=9781424481835&rft_id=info:doi/10.1109/ISTEL.2010.5734148&rft_dat=%3Cieee_6IE%3E5734148%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1424481848&rft.eisbn_list=9781424481842&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5734148&rfr_iscdi=true |