Combining statistical models using modified spectral subtraction method for embedded system
Speech enhancement aims at improving the overall speech signal perceptual quality using different audio signal processing techniques. Filtering techniques, spectral restoration and model-based methods are the three fundamental classes of speech enhancement algorithms for noise reduction. With mobile...
Gespeichert in:
Veröffentlicht in: | Microprocessors and microsystems 2020-03, Vol.73, p.102957, Article 102957 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | 102957 |
container_title | Microprocessors and microsystems |
container_volume | 73 |
creator | Balaji, V.R. S, Maheswaran Rajesh Babu, M. Kowsigan, M. E., Prabhu K, Venkatachalam |
description | Speech enhancement aims at improving the overall speech signal perceptual quality using different audio signal processing techniques. Filtering techniques, spectral restoration and model-based methods are the three fundamental classes of speech enhancement algorithms for noise reduction. With mobile devices increased usage, the demand for algorithms processing also increases. As the microphones that capture the voice of the speaker are at considerable distance in most of the devices, noise are getting added thereby degrading the quality of the speech signal. No single theorist's stone or minimization standard has been discovered so far for speech enhancement. In this work, we have combined the statistical models along with machine learning algorithm to improve the results thereby resulting in robust communication. Experimentation results on AURORA 2 database shows us improved results over the state of the art methods discussed in the literature. |
doi_str_mv | 10.1016/j.micpro.2019.102957 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2377330862</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0141933119304600</els_id><sourcerecordid>2377330862</sourcerecordid><originalsourceid>FETCH-LOGICAL-c400t-f10d7f2fe839858f394d5b763eb2d7ba6a14693cd7a9df56d6fccd1fc9addf1e3</originalsourceid><addsrcrecordid>eNp9kEtLxDAQx4MouK5-Aw8Fz13zaJPmIsjiCxa86MlDaJOJpmybNUmF_fam1LOnYeb_GPghdE3whmDCb_vN4PQh-A3FROYTlbU4QSvSCFrKivFTtMKkIqVkjJyjixh7jHGNOV2hj60fOje68bOIqU0uJqfbfTF4A_tYTHEW8uKsA1PEA-gUshynLk-dnB-LAdKXN4X1oYChA2Nm4zEmGC7RmW33Ea7-5hq9Pz68bZ_L3evTy_Z-V-oK41Rago2w1ELDZFM3lsnK1J3gDDpqRNfyllRcMm1EK42tueFWa0Oslq0xlgBbo5ulNyP4niAm1fspjPmlokwIxnDDaXZVi0sHH2MAqw7BDW04KoLVjFH1asGoZoxqwZhjd0ss84AfB0FF7WDUYFzINJTx7v-CX4qcgBE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2377330862</pqid></control><display><type>article</type><title>Combining statistical models using modified spectral subtraction method for embedded system</title><source>Access via ScienceDirect (Elsevier)</source><creator>Balaji, V.R. ; S, Maheswaran ; Rajesh Babu, M. ; Kowsigan, M. ; E., Prabhu ; K, Venkatachalam</creator><creatorcontrib>Balaji, V.R. ; S, Maheswaran ; Rajesh Babu, M. ; Kowsigan, M. ; E., Prabhu ; K, Venkatachalam</creatorcontrib><description>Speech enhancement aims at improving the overall speech signal perceptual quality using different audio signal processing techniques. Filtering techniques, spectral restoration and model-based methods are the three fundamental classes of speech enhancement algorithms for noise reduction. With mobile devices increased usage, the demand for algorithms processing also increases. As the microphones that capture the voice of the speaker are at considerable distance in most of the devices, noise are getting added thereby degrading the quality of the speech signal. No single theorist's stone or minimization standard has been discovered so far for speech enhancement. In this work, we have combined the statistical models along with machine learning algorithm to improve the results thereby resulting in robust communication. Experimentation results on AURORA 2 database shows us improved results over the state of the art methods discussed in the literature.</description><identifier>ISSN: 0141-9331</identifier><identifier>EISSN: 1872-9436</identifier><identifier>DOI: 10.1016/j.micpro.2019.102957</identifier><language>eng</language><publisher>Kidlington: Elsevier B.V</publisher><subject>Algorithms ; Electronic devices ; Embedded systems ; Experimentation ; Linear models ; Machine learning ; Microphones ; Noise reduction ; Precision and recall ; Restoration ; Signal processing ; Signal quality ; Speech enhancement ; Speech processing ; Statistical models ; Subtraction ; Support vector machines ; Voice communication</subject><ispartof>Microprocessors and microsystems, 2020-03, Vol.73, p.102957, Article 102957</ispartof><rights>2019</rights><rights>Copyright Elsevier BV Mar 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c400t-f10d7f2fe839858f394d5b763eb2d7ba6a14693cd7a9df56d6fccd1fc9addf1e3</citedby><cites>FETCH-LOGICAL-c400t-f10d7f2fe839858f394d5b763eb2d7ba6a14693cd7a9df56d6fccd1fc9addf1e3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.micpro.2019.102957$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Balaji, V.R.</creatorcontrib><creatorcontrib>S, Maheswaran</creatorcontrib><creatorcontrib>Rajesh Babu, M.</creatorcontrib><creatorcontrib>Kowsigan, M.</creatorcontrib><creatorcontrib>E., Prabhu</creatorcontrib><creatorcontrib>K, Venkatachalam</creatorcontrib><title>Combining statistical models using modified spectral subtraction method for embedded system</title><title>Microprocessors and microsystems</title><description>Speech enhancement aims at improving the overall speech signal perceptual quality using different audio signal processing techniques. Filtering techniques, spectral restoration and model-based methods are the three fundamental classes of speech enhancement algorithms for noise reduction. With mobile devices increased usage, the demand for algorithms processing also increases. As the microphones that capture the voice of the speaker are at considerable distance in most of the devices, noise are getting added thereby degrading the quality of the speech signal. No single theorist's stone or minimization standard has been discovered so far for speech enhancement. In this work, we have combined the statistical models along with machine learning algorithm to improve the results thereby resulting in robust communication. Experimentation results on AURORA 2 database shows us improved results over the state of the art methods discussed in the literature.</description><subject>Algorithms</subject><subject>Electronic devices</subject><subject>Embedded systems</subject><subject>Experimentation</subject><subject>Linear models</subject><subject>Machine learning</subject><subject>Microphones</subject><subject>Noise reduction</subject><subject>Precision and recall</subject><subject>Restoration</subject><subject>Signal processing</subject><subject>Signal quality</subject><subject>Speech enhancement</subject><subject>Speech processing</subject><subject>Statistical models</subject><subject>Subtraction</subject><subject>Support vector machines</subject><subject>Voice communication</subject><issn>0141-9331</issn><issn>1872-9436</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp9kEtLxDAQx4MouK5-Aw8Fz13zaJPmIsjiCxa86MlDaJOJpmybNUmF_fam1LOnYeb_GPghdE3whmDCb_vN4PQh-A3FROYTlbU4QSvSCFrKivFTtMKkIqVkjJyjixh7jHGNOV2hj60fOje68bOIqU0uJqfbfTF4A_tYTHEW8uKsA1PEA-gUshynLk-dnB-LAdKXN4X1oYChA2Nm4zEmGC7RmW33Ea7-5hq9Pz68bZ_L3evTy_Z-V-oK41Rago2w1ELDZFM3lsnK1J3gDDpqRNfyllRcMm1EK42tueFWa0Oslq0xlgBbo5ulNyP4niAm1fspjPmlokwIxnDDaXZVi0sHH2MAqw7BDW04KoLVjFH1asGoZoxqwZhjd0ss84AfB0FF7WDUYFzINJTx7v-CX4qcgBE</recordid><startdate>202003</startdate><enddate>202003</enddate><creator>Balaji, V.R.</creator><creator>S, Maheswaran</creator><creator>Rajesh Babu, M.</creator><creator>Kowsigan, M.</creator><creator>E., Prabhu</creator><creator>K, Venkatachalam</creator><general>Elsevier B.V</general><general>Elsevier BV</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>202003</creationdate><title>Combining statistical models using modified spectral subtraction method for embedded system</title><author>Balaji, V.R. ; S, Maheswaran ; Rajesh Babu, M. ; Kowsigan, M. ; E., Prabhu ; K, Venkatachalam</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c400t-f10d7f2fe839858f394d5b763eb2d7ba6a14693cd7a9df56d6fccd1fc9addf1e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Electronic devices</topic><topic>Embedded systems</topic><topic>Experimentation</topic><topic>Linear models</topic><topic>Machine learning</topic><topic>Microphones</topic><topic>Noise reduction</topic><topic>Precision and recall</topic><topic>Restoration</topic><topic>Signal processing</topic><topic>Signal quality</topic><topic>Speech enhancement</topic><topic>Speech processing</topic><topic>Statistical models</topic><topic>Subtraction</topic><topic>Support vector machines</topic><topic>Voice communication</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Balaji, V.R.</creatorcontrib><creatorcontrib>S, Maheswaran</creatorcontrib><creatorcontrib>Rajesh Babu, M.</creatorcontrib><creatorcontrib>Kowsigan, M.</creatorcontrib><creatorcontrib>E., Prabhu</creatorcontrib><creatorcontrib>K, Venkatachalam</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Microprocessors and microsystems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Balaji, V.R.</au><au>S, Maheswaran</au><au>Rajesh Babu, M.</au><au>Kowsigan, M.</au><au>E., Prabhu</au><au>K, Venkatachalam</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Combining statistical models using modified spectral subtraction method for embedded system</atitle><jtitle>Microprocessors and microsystems</jtitle><date>2020-03</date><risdate>2020</risdate><volume>73</volume><spage>102957</spage><pages>102957-</pages><artnum>102957</artnum><issn>0141-9331</issn><eissn>1872-9436</eissn><abstract>Speech enhancement aims at improving the overall speech signal perceptual quality using different audio signal processing techniques. Filtering techniques, spectral restoration and model-based methods are the three fundamental classes of speech enhancement algorithms for noise reduction. With mobile devices increased usage, the demand for algorithms processing also increases. As the microphones that capture the voice of the speaker are at considerable distance in most of the devices, noise are getting added thereby degrading the quality of the speech signal. No single theorist's stone or minimization standard has been discovered so far for speech enhancement. In this work, we have combined the statistical models along with machine learning algorithm to improve the results thereby resulting in robust communication. Experimentation results on AURORA 2 database shows us improved results over the state of the art methods discussed in the literature.</abstract><cop>Kidlington</cop><pub>Elsevier B.V</pub><doi>10.1016/j.micpro.2019.102957</doi></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0141-9331 |
ispartof | Microprocessors and microsystems, 2020-03, Vol.73, p.102957, Article 102957 |
issn | 0141-9331 1872-9436 |
language | eng |
recordid | cdi_proquest_journals_2377330862 |
source | Access via ScienceDirect (Elsevier) |
subjects | Algorithms Electronic devices Embedded systems Experimentation Linear models Machine learning Microphones Noise reduction Precision and recall Restoration Signal processing Signal quality Speech enhancement Speech processing Statistical models Subtraction Support vector machines Voice communication |
title | Combining statistical models using modified spectral subtraction method for embedded system |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T13%3A19%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Combining%20statistical%20models%20using%20modified%20spectral%20subtraction%20method%20for%20embedded%20system&rft.jtitle=Microprocessors%20and%20microsystems&rft.au=Balaji,%20V.R.&rft.date=2020-03&rft.volume=73&rft.spage=102957&rft.pages=102957-&rft.artnum=102957&rft.issn=0141-9331&rft.eissn=1872-9436&rft_id=info:doi/10.1016/j.micpro.2019.102957&rft_dat=%3Cproquest_cross%3E2377330862%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2377330862&rft_id=info:pmid/&rft_els_id=S0141933119304600&rfr_iscdi=true |