{"id":"https://openalex.org/W2981992480","doi":"https://doi.org/10.1109/icassp40776.2020.9054271","title":"SLOGD: Speaker Location Guided Deflation Approach to Speech Separation","display_name":"SLOGD: Speaker Location Guided Deflation Approach to Speech Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981992480","doi":"https://doi.org/10.1109/icassp40776.2020.9054271","mag":"2981992480"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.11131","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sunit Sivasankaran","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sunit Sivasankaran","raw_affiliation_strings":["CNRS, Inria, LORIA, Universit\u00e9 de Lorraine, Nancy, France","Speech Modeling for Facilitating Oral-Based Communication"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS, Inria, LORIA, Universit\u00e9 de Lorraine, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065635001","display_name":"Emmanuel Vincent","orcid":"https://orcid.org/0000-0002-0183-7289"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["CNRS, Inria, LORIA, Universit\u00e9 de Lorraine, Nancy, France","Speech Modeling for Facilitating Oral-Based Communication"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS, Inria, LORIA, Universit\u00e9 de Lorraine, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046546502","display_name":"Dominique Fohr","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dominique Fohr","raw_affiliation_strings":["CNRS, Inria, LORIA, Universit\u00e9 de Lorraine, Nancy, France","Speech Modeling for Facilitating Oral-Based Communication"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS, Inria, LORIA, Universit\u00e9 de Lorraine, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00684887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6409","last_page":"6413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deflation","display_name":"Deflation","score":0.7851969599723816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6735434532165527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6438197493553162},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4654600918292999},{"id":"https://openalex.org/keywords/monetary-economics","display_name":"Monetary economics","score":0.08004757761955261},{"id":"https://openalex.org/keywords/monetary-policy","display_name":"Monetary policy","score":0.07619723677635193},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07197737693786621},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.05779096484184265}],"concepts":[{"id":"https://openalex.org/C8112001","wikidata":"https://www.wikidata.org/wiki/Q161081","display_name":"Deflation","level":3,"score":0.7851969599723816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6735434532165527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6438197493553162},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4654600918292999},{"id":"https://openalex.org/C556758197","wikidata":"https://www.wikidata.org/wiki/Q580018","display_name":"Monetary economics","level":1,"score":0.08004757761955261},{"id":"https://openalex.org/C126285488","wikidata":"https://www.wikidata.org/wiki/Q178476","display_name":"Monetary policy","level":2,"score":0.07619723677635193},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07197737693786621},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.05779096484184265}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054271","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054271","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.11131","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11131","pdf_url":"https://arxiv.org/pdf/1910.11131","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02355613v1","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02355613","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-02355613","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:HAL:hal-02355613v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02355613","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1910.11131","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.11131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/qhct-jk13","is_oa":true,"landing_page_url":"https://doi.org/10.17023/qhct-jk13","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.11131","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11131","pdf_url":"https://arxiv.org/pdf/1910.11131","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3872131408","display_name":"Robust voice command adapted to the user and to the context for AAL","funder_award_id":"ANR-16-CE33-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2046317813","https://openalex.org/W2050616618","https://openalex.org/W2101045344","https://openalex.org/W2221409856","https://openalex.org/W2514741789","https://openalex.org/W2561557072","https://openalex.org/W2568308529","https://openalex.org/W2734774145","https://openalex.org/W2750446090","https://openalex.org/W2786625961","https://openalex.org/W2884797218","https://openalex.org/W2889061314","https://openalex.org/W2891054259","https://openalex.org/W2900893004","https://openalex.org/W2909607850","https://openalex.org/W2943934118","https://openalex.org/W2952218014","https://openalex.org/W2963488660","https://openalex.org/W2964342924","https://openalex.org/W2972449503","https://openalex.org/W2972767900","https://openalex.org/W3043433769","https://openalex.org/W6758080106","https://openalex.org/W6769975201"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2370469255","https://openalex.org/W2389301650","https://openalex.org/W1993035291","https://openalex.org/W2380526272","https://openalex.org/W2388481350","https://openalex.org/W2387663987","https://openalex.org/W2593136982","https://openalex.org/W2182958548"],"abstract_inverted_index":{"Speech":[0],"separation":[1,116],"is":[2,62],"the":[3,20,33,42,45,56,65,69,74,87,113],"process":[4],"of":[5,44,73,86,105],"separating":[6],"multiple":[7],"speakers":[8],"from":[9,64],"an":[10],"audio":[11],"recording.":[12],"In":[13,36],"this":[14],"work":[15],"we":[16,31,39],"propose":[17],"to":[18,50,55],"separate":[19],"sources":[21,34],"using":[22,91],"a":[23,52,81,97,103,108],"Speaker":[24],"LOcalization":[25],"Guided":[26],"Deflation":[27],"(SLOGD)":[28],"approach":[29],"wherein":[30],"estimate":[32,41,51],"iteratively.":[35],"each":[37],"iteration":[38],"first":[40],"location":[43,70],"speaker":[46],"and":[47,71,117],"use":[48],"it":[49],"mask":[53,72],"corresponding":[54],"localized":[57],"speaker.":[58],"The":[59,99],"estimated":[60],"source":[61],"removed":[63],"mixture":[66],"before":[67],"estimating":[68],"next":[75],"source.":[76],"Experiments":[77],"are":[78],"conducted":[79],"on":[80],"reverberated,":[82],"noisy":[83],"multichannel":[84],"version":[85],"well-studied":[88],"WSJ-2MIX":[89],"dataset":[90],"word":[92],"error":[93],"rate":[94],"(WER)":[95],"as":[96],"metric.":[98],"proposed":[100],"method":[101],"achieves":[102],"WER":[104],"44.2":[106],"%,":[107],"34%":[109],"relative":[110,119],"improvement":[111,120],"over":[112,121],"system":[114],"without":[115],"17%":[118],"Conv-TasNet.":[122]},"counts_by_year":[],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}