{"id":"https://openalex.org/W2982001417","doi":"https://doi.org/10.1109/icassp40776.2020.9054693","title":"Adaptive Blind Audio Source Extraction Supervised By Dominant Speaker Identification Using X-Vectors","display_name":"Adaptive Blind Audio Source Extraction Supervised By Dominant Speaker Identification Using X-Vectors","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982001417","doi":"https://doi.org/10.1109/icassp40776.2020.9054693","mag":"2982001417"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054693","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.11824","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025763449","display_name":"Jakub Jansk\u00fd","orcid":"https://orcid.org/0000-0001-7151-6723"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Jakub Jansky","raw_affiliation_strings":["Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102731459","display_name":"Ji\u0159\u00ed M\u00e1lek","orcid":"https://orcid.org/0000-0002-5864-0196"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jiri Malek","raw_affiliation_strings":["Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037957439","display_name":"Jaroslav \u010cmejla","orcid":null},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jaroslav Cmejla","raw_affiliation_strings":["Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078183499","display_name":"Tom\u00e1\u0161 Kounovsk\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tomas Kounovsky","raw_affiliation_strings":["Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040855107","display_name":"Zbyn\u011bk Koldovsk\u00fd","orcid":"https://orcid.org/0000-0002-1791-5675"},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Zbynek Koldovsky","raw_affiliation_strings":["Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089093629","display_name":"Jind\u0159ich \u017d\u010f\u00e1nsk\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I147009085","display_name":"Technical University of Liberec","ror":"https://ror.org/02jtk7k02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I147009085"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jindrich Zd'ansky","raw_affiliation_strings":["Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Acoustic Signal Analysis and Processing Group, Technical University of Liberec, Liberec, Czech Republic","institution_ids":["https://openalex.org/I147009085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025763449"],"corresponding_institution_ids":["https://openalex.org/I147009085"],"apc_list":null,"apc_paid":null,"fwci":0.59110271,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.64418712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"676","last_page":"680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9997000098228455,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7315199375152588},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6245107054710388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6135041117668152},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.590796709060669},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5717864632606506},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5521098375320435},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4751453399658203},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4520329535007477},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44068434834480286},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3982802629470825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39650237560272217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7315199375152588},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6245107054710388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6135041117668152},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.590796709060669},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5717864632606506},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5521098375320435},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4751453399658203},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4520329535007477},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44068434834480286},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3982802629470825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39650237560272217},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054693","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:1910.11824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11824","pdf_url":"https://arxiv.org/pdf/1910.11824","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":null,"raw_type":"text"},{"id":"mag:2982001417","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.11824.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.11824","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.11824","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.11824","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11824","pdf_url":"https://arxiv.org/pdf/1910.11824","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982001417.pdf","grobid_xml":"https://content.openalex.org/works/W2982001417.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1543386260","https://openalex.org/W1589137271","https://openalex.org/W2072548008","https://openalex.org/W2150769028","https://openalex.org/W2402146185","https://openalex.org/W2638067502","https://openalex.org/W2657204326","https://openalex.org/W2726515241","https://openalex.org/W2749510669","https://openalex.org/W2765844457","https://openalex.org/W2766352194","https://openalex.org/W2890964092","https://openalex.org/W2938358845","https://openalex.org/W2946546503","https://openalex.org/W2951130829","https://openalex.org/W2951431217","https://openalex.org/W2997688633","https://openalex.org/W6635152626","https://openalex.org/W6668479384","https://openalex.org/W6712930963","https://openalex.org/W6740167877"],"related_works":["https://openalex.org/W3015256813","https://openalex.org/W3213715318","https://openalex.org/W1995986507","https://openalex.org/W20928449","https://openalex.org/W281262342","https://openalex.org/W2000393873","https://openalex.org/W2546214126","https://openalex.org/W2099124598","https://openalex.org/W2566378066","https://openalex.org/W50589544","https://openalex.org/W2752655524","https://openalex.org/W2300568240","https://openalex.org/W3119878802","https://openalex.org/W2123311195","https://openalex.org/W2068008348","https://openalex.org/W2855570824","https://openalex.org/W2030723086","https://openalex.org/W3130933400","https://openalex.org/W2387923902","https://openalex.org/W2752079466"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,37,68,96,99],"novel":[3],"algorithm":[4,32],"for":[5],"adaptive":[6],"blind":[7],"audio":[8],"source":[9,43],"extraction.":[10],"The":[11,31,60,76,90],"proposed":[12,91],"method":[13,51],"is":[14,33,62,93],"based":[15,63],"on":[16,64],"independent":[17],"vector":[18],"analysis":[19],"and":[20,105],"utilizes":[21],"the":[22,42,50,54,57,65,72,79,83],"auxiliary":[23],"function":[24],"optimization":[25],"to":[26,41],"achieve":[27],"high":[28],"convergence":[29],"speed.":[30],"partially":[34],"supervised":[35],"by":[36],"pilot":[38,61],"signal":[39],"related":[40],"of":[44,56,67,78,85],"interest":[45],"(SOI),":[46],"which":[47],"ensures":[48],"that":[49],"correctly":[52],"extracts":[53],"utterance":[55],"desired":[58],"speaker.":[59],"identification":[66],"dominant":[69],"speaker":[70],"in":[71,82,95],"mixture":[73],"using":[74],"x-vectors.":[75],"properties":[77],"x-vectors":[80],"computed":[81],"presence":[84],"cross-talk":[86],"are":[87],"experimentally":[88],"analyzed.":[89],"approach":[92],"verified":[94],"scenario":[97],"with":[98],"moving":[100],"SOI,":[101],"static":[102],"interfering":[103],"speaker,":[104],"environmental":[106],"noise.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}