{"id":"https://openalex.org/W4224917914","doi":"https://doi.org/10.1109/icassp43922.2022.9747771","title":"Multi-Channel Speaker Verification with Conv-Tasnet Based Beamformer","display_name":"Multi-Channel Speaker Verification with Conv-Tasnet Based Beamformer","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917914","doi":"https://doi.org/10.1109/icassp43922.2022.9747771"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747771","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055201620","display_name":"Ladislav Mo\u0161ner","orcid":"https://orcid.org/0000-0001-8175-2244"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Ladislav Mosner","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Oldrich Plchot","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Honza Cernocky","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":1.292,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81158025,"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":"7982","last_page":"7986"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7746301889419556},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6649043560028076},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5713329315185547},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5276005864143372},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5269901156425476},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.500018835067749},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.43470078706741333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37054920196533203},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3484123647212982},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22719377279281616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1071479320526123},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09969910979270935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746301889419556},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6649043560028076},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5713329315185547},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5276005864143372},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5269901156425476},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.500018835067749},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.43470078706741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37054920196533203},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3484123647212982},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22719377279281616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1071479320526123},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09969910979270935},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747771","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W46095808","https://openalex.org/W1494198834","https://openalex.org/W2066218102","https://openalex.org/W2117678320","https://openalex.org/W2158143227","https://openalex.org/W2168729028","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2580221632","https://openalex.org/W2591810467","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2748488820","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2939497224","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963040451","https://openalex.org/W2972345734","https://openalex.org/W2972425344","https://openalex.org/W2972526647","https://openalex.org/W2972693890","https://openalex.org/W2972992051","https://openalex.org/W3008090241","https://openalex.org/W3015199127","https://openalex.org/W3015503328","https://openalex.org/W3015679215","https://openalex.org/W3015788098","https://openalex.org/W3015791598","https://openalex.org/W3016094953","https://openalex.org/W3016912202","https://openalex.org/W3024388846","https://openalex.org/W3099330747","https://openalex.org/W3103152812","https://openalex.org/W3111481301","https://openalex.org/W3163652268","https://openalex.org/W3212414183","https://openalex.org/W4288558760","https://openalex.org/W6688816777","https://openalex.org/W6732646663","https://openalex.org/W6760112457","https://openalex.org/W6787439801"],"related_works":["https://openalex.org/W1970408","https://openalex.org/W5708970","https://openalex.org/W6222964","https://openalex.org/W1496815","https://openalex.org/W8932171","https://openalex.org/W9997782","https://openalex.org/W9420449","https://openalex.org/W14578209","https://openalex.org/W3703470","https://openalex.org/W589191"],"abstract_inverted_index":{"We":[0,34,61,88,120],"focus":[1],"on":[2,113,134],"the":[3,30,65,91,94,131],"problem":[4,92],"of":[5,20,67,73,93,96,106],"speaker":[6,85],"recognition":[7],"in":[8],"far-field":[9],"multichannel":[10,99],"data.":[11],"The":[12,109],"main":[13],"contribution":[14],"is":[15,111],"introducing":[16],"an":[17],"alternative":[18],"way":[19],"predicting":[21],"spatial":[22],"covariance":[23],"matrices":[24],"(SCMs)":[25],"for":[26],"a":[27,39,97,125,135],"beamformer":[28],"from":[29],"time":[31],"domain":[32],"signal.":[33],"propose":[35],"to":[36,48,55,70],"use":[37],"ConvTasNet,":[38],"well-known":[40],"source":[41],"separation":[42],"model,":[43],"and":[44,58,75,77,116],"we":[45,79],"adapt":[46],"it":[47,54],"perform":[49],"speech":[50,57,74],"enhancement":[51],"by":[52,102],"forcing":[53],"separate":[56],"additive":[59],"noise.":[60],"experiment":[62],"with":[63,124,137],"using":[64,103],"STFT":[66],"Conv-TasNet":[68],"outputs":[69],"obtain":[71],"SCMs":[72],"noise,":[76],"finally,":[78],"fine-tune":[80],"this":[81],"multi-channel":[82],"frontend":[83],"w.r.t.":[84],"verification":[86],"objective.":[87],"successfully":[89],"tackle":[90],"lack":[95],"realistic":[98],"training":[100],"set":[101],"simulated":[104,117],"data":[105],"MultiSV":[107],"corpus.":[108],"analysis":[110],"performed":[112],"its":[114],"retransmitted":[115],"test":[118],"parts.":[119],"achieve":[121],"consistent":[122],"improvements":[123],"2.7":[126],"times":[127],"smaller":[128],"model":[129],"than":[130],"baseline":[132],"based":[133],"scheme":[136],"mask":[138],"estimating":[139],"NN.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
