Source localization and separation using Random Sample Consensus with phase cues

In this paper we present a system for localization and separation of multiple speech sources using phase cues. The novelty of this method is the use of Random Sample Consensus (RANSAC) approach to find consistency of interaural phase differences (IPDs) across the whole frequency range. This approach...

Full description

Saved in:
Bibliographic Details
Main Authors: Litwic, L., Jackson, P. J. B.
Format: Conference Proceeding
Language:English
Subjects:
Data models
Delay effects
Estimation
Histograms
Signal processing algorithms
Speech
Time frequency analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 340
container_issue
container_start_page 337
container_title
container_volume
creator Litwic, L.
Jackson, P. J. B.
description In this paper we present a system for localization and separation of multiple speech sources using phase cues. The novelty of this method is the use of Random Sample Consensus (RANSAC) approach to find consistency of interaural phase differences (IPDs) across the whole frequency range. This approach is inherently free from phase ambiguity problems and enables all phase data to contribute to localization. Another property of RANSAC is its robustness against outliers which enables multiple source localization with phase data contaminated by reverberation noise. Results of RANSAC based localization are fed into a mixture model to generate time-frequency binary masks for separation. System performance is compared against other well known methods and shows similar or improved performance in reverberant conditions.
doi_str_mv 10.1109/ASPAA.2011.6082334
format conference_proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6082334</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6082334</ieee_id><sourcerecordid>6082334</sourcerecordid><originalsourceid>FETCH-LOGICAL-i219t-15b2706050f4dcfd5952408215a3c49dfa9a573ea185e61524231a8602579ddd3</originalsourceid><addsrcrecordid>eNpFkFtLxDAQheMNXNf9A_qSP9Caya3NYyneYMHFKvi2jE3qRnqjaRH99VZ2wfNymPPBMHMIuQIWAzBzkxWbLIs5A4g1S7kQ8ohcgFRJwrQBOCYLMDKJQHNz8g_42-kfEBAB6PScrEL4ZLM0T1IlF2RTdNNQOlp3Jdb-B0fftRRbS4PrcdiPU_DtB32e066hBTZ97WjetcG1YQr0y4872u8wOFpOLlySswrr4FYHX5LXu9uX_CFaP90_5tk68hzMGIF65_N9TLFK2rKyyigu57dAoSilsRUaVIlwCKlyGmbIBWCqGVeJsdaKJbne7_XOuW0_-AaH7-2hGfELlI1TFQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Source localization and separation using Random Sample Consensus with phase cues</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Litwic, L. ; Jackson, P. J. B.</creator><creatorcontrib>Litwic, L. ; Jackson, P. J. B.</creatorcontrib><description>In this paper we present a system for localization and separation of multiple speech sources using phase cues. The novelty of this method is the use of Random Sample Consensus (RANSAC) approach to find consistency of interaural phase differences (IPDs) across the whole frequency range. This approach is inherently free from phase ambiguity problems and enables all phase data to contribute to localization. Another property of RANSAC is its robustness against outliers which enables multiple source localization with phase data contaminated by reverberation noise. Results of RANSAC based localization are fed into a mixture model to generate time-frequency binary masks for separation. System performance is compared against other well known methods and shows similar or improved performance in reverberant conditions.</description><identifier>ISSN: 1931-1168</identifier><identifier>ISBN: 145770692X</identifier><identifier>ISBN: 9781457706929</identifier><identifier>EISSN: 1947-1629</identifier><identifier>EISBN: 1457706911</identifier><identifier>EISBN: 1457706938</identifier><identifier>EISBN: 9781457706912</identifier><identifier>EISBN: 9781457706936</identifier><identifier>DOI: 10.1109/ASPAA.2011.6082334</identifier><language>eng</language><publisher>IEEE</publisher><subject>Data models ; Delay effects ; Estimation ; Histograms ; Signal processing algorithms ; Speech ; Time frequency analysis</subject><ispartof>2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2011, p.337-340</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/6082334$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6082334$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Litwic, L.</creatorcontrib><creatorcontrib>Jackson, P. J. B.</creatorcontrib><title>Source localization and separation using Random Sample Consensus with phase cues</title><title>2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)</title><addtitle>ASPAA</addtitle><description>In this paper we present a system for localization and separation of multiple speech sources using phase cues. The novelty of this method is the use of Random Sample Consensus (RANSAC) approach to find consistency of interaural phase differences (IPDs) across the whole frequency range. This approach is inherently free from phase ambiguity problems and enables all phase data to contribute to localization. Another property of RANSAC is its robustness against outliers which enables multiple source localization with phase data contaminated by reverberation noise. Results of RANSAC based localization are fed into a mixture model to generate time-frequency binary masks for separation. System performance is compared against other well known methods and shows similar or improved performance in reverberant conditions.</description><subject>Data models</subject><subject>Delay effects</subject><subject>Estimation</subject><subject>Histograms</subject><subject>Signal processing algorithms</subject><subject>Speech</subject><subject>Time frequency analysis</subject><issn>1931-1168</issn><issn>1947-1629</issn><isbn>145770692X</isbn><isbn>9781457706929</isbn><isbn>1457706911</isbn><isbn>1457706938</isbn><isbn>9781457706912</isbn><isbn>9781457706936</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpFkFtLxDAQheMNXNf9A_qSP9Caya3NYyneYMHFKvi2jE3qRnqjaRH99VZ2wfNymPPBMHMIuQIWAzBzkxWbLIs5A4g1S7kQ8ohcgFRJwrQBOCYLMDKJQHNz8g_42-kfEBAB6PScrEL4ZLM0T1IlF2RTdNNQOlp3Jdb-B0fftRRbS4PrcdiPU_DtB32e066hBTZ97WjetcG1YQr0y4872u8wOFpOLlySswrr4FYHX5LXu9uX_CFaP90_5tk68hzMGIF65_N9TLFK2rKyyigu57dAoSilsRUaVIlwCKlyGmbIBWCqGVeJsdaKJbne7_XOuW0_-AaH7-2hGfELlI1TFQ</recordid><startdate>20110101</startdate><enddate>20110101</enddate><creator>Litwic, L.</creator><creator>Jackson, P. J. B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20110101</creationdate><title>Source localization and separation using Random Sample Consensus with phase cues</title><author>Litwic, L. ; Jackson, P. J. B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i219t-15b2706050f4dcfd5952408215a3c49dfa9a573ea185e61524231a8602579ddd3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Data models</topic><topic>Delay effects</topic><topic>Estimation</topic><topic>Histograms</topic><topic>Signal processing algorithms</topic><topic>Speech</topic><topic>Time frequency analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Litwic, L.</creatorcontrib><creatorcontrib>Jackson, P. J. B.</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>Litwic, L.</au><au>Jackson, P. J. B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Source localization and separation using Random Sample Consensus with phase cues</atitle><btitle>2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)</btitle><stitle>ASPAA</stitle><date>2011-01-01</date><risdate>2011</risdate><spage>337</spage><epage>340</epage><pages>337-340</pages><issn>1931-1168</issn><eissn>1947-1629</eissn><isbn>145770692X</isbn><isbn>9781457706929</isbn><eisbn>1457706911</eisbn><eisbn>1457706938</eisbn><eisbn>9781457706912</eisbn><eisbn>9781457706936</eisbn><abstract>In this paper we present a system for localization and separation of multiple speech sources using phase cues. The novelty of this method is the use of Random Sample Consensus (RANSAC) approach to find consistency of interaural phase differences (IPDs) across the whole frequency range. This approach is inherently free from phase ambiguity problems and enables all phase data to contribute to localization. Another property of RANSAC is its robustness against outliers which enables multiple source localization with phase data contaminated by reverberation noise. Results of RANSAC based localization are fed into a mixture model to generate time-frequency binary masks for separation. System performance is compared against other well known methods and shows similar or improved performance in reverberant conditions.</abstract><pub>IEEE</pub><doi>10.1109/ASPAA.2011.6082334</doi><tpages>4</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1931-1168
ispartof 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2011, p.337-340
issn 1931-1168
1947-1629
language eng
recordid cdi_ieee_primary_6082334
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Data models
Delay effects
Estimation
Histograms
Signal processing algorithms
Speech
Time frequency analysis
title Source localization and separation using Random Sample Consensus with phase cues
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T05%3A49%3A35IST&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=Source%20localization%20and%20separation%20using%20Random%20Sample%20Consensus%20with%20phase%20cues&rft.btitle=2011%20IEEE%20Workshop%20on%20Applications%20of%20Signal%20Processing%20to%20Audio%20and%20Acoustics%20(WASPAA)&rft.au=Litwic,%20L.&rft.date=2011-01-01&rft.spage=337&rft.epage=340&rft.pages=337-340&rft.issn=1931-1168&rft.eissn=1947-1629&rft.isbn=145770692X&rft.isbn_list=9781457706929&rft_id=info:doi/10.1109/ASPAA.2011.6082334&rft.eisbn=1457706911&rft.eisbn_list=1457706938&rft.eisbn_list=9781457706912&rft.eisbn_list=9781457706936&rft_dat=%3Cieee_6IE%3E6082334%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i219t-15b2706050f4dcfd5952408215a3c49dfa9a573ea185e61524231a8602579ddd3%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=6082334&rfr_iscdi=true