{"id":"https://openalex.org/W3008090241","doi":"https://doi.org/10.1109/asru46091.2019.9003932","title":"Speaker Verification with Application-Aware Beamforming","display_name":"Speaker Verification with Application-Aware Beamforming","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008090241","doi":"https://doi.org/10.1109/asru46091.2019.9003932","mag":"3008090241"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003932","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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, IT4I Centre of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, IT4I Centre of Excellence, 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, IT4I Centre of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, IT4I Centre of Excellence, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043239262","display_name":"Johan Rohdin","orcid":"https://orcid.org/0000-0003-0978-2064"},"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":"Johan Rohdin","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, IT4I Centre of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, IT4I Centre of Excellence, 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, IT4I Centre of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, IT4I Centre of Excellence, 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 Cernocky","raw_affiliation_strings":["Brno University of Technology, Faculty of Information Technology, IT4I Centre of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of Information Technology, IT4I Centre of Excellence, 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":0.7646,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70696904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"139","issue":null,"first_page":"411","last_page":"418"},"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":0.9983999729156494,"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":0.7939016819000244},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6922739744186401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.608742356300354},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5605928301811218},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.49848127365112305},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4643882215023041},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44299745559692383},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43317484855651855},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.43074190616607666},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3599984645843506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3498693108558655},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32847368717193604},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0730573832988739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939016819000244},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6922739744186401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.608742356300354},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5605928301811218},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.49848127365112305},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4643882215023041},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44299745559692383},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43317484855651855},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.43074190616607666},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3599984645843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3498693108558655},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32847368717193604},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0730573832988739},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003932","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2066218102","https://openalex.org/W2117678320","https://openalex.org/W2121812409","https://openalex.org/W2129227482","https://openalex.org/W2148613904","https://openalex.org/W2150769028","https://openalex.org/W2158143227","https://openalex.org/W2343471890","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2407277936","https://openalex.org/W2506203739","https://openalex.org/W2517616541","https://openalex.org/W2589857635","https://openalex.org/W2640112133","https://openalex.org/W2699350432","https://openalex.org/W2748488820","https://openalex.org/W2796485741","https://openalex.org/W2916024349","https://openalex.org/W2938358845","https://openalex.org/W2963040451","https://openalex.org/W2966212213","https://openalex.org/W2973147881","https://openalex.org/W4288558760","https://openalex.org/W6631362777","https://openalex.org/W6766475400"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W2767070583","https://openalex.org/W4235705411","https://openalex.org/W2784052451","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2120771489"],"abstract_inverted_index":{"Multichannel":[0],"speech":[1,10],"processing":[2],"applications":[3],"usually":[4],"employ":[5],"beamformers":[6],"as":[7],"means":[8],"of":[9,57,88],"enhancement":[11],"through":[12],"spatial":[13],"filtering.":[14],"Beamformers":[15],"with":[16,31,80],"learnable":[17],"parameters":[18],"require":[19],"training":[20,87],"to":[21,119],"minimize":[22],"a":[23,40,72,95],"loss":[24],"function":[25],"that":[26,53,77,85,125],"is":[27,67],"not":[28],"necessarily":[29],"correlated":[30],"the":[32,65,89,99,107,121],"final":[33],"objective.":[34],"In":[35,62],"this":[36],"paper,":[37],"we":[38],"present":[39],"framework":[41],"employing":[42],"recent":[43],"neural":[44],"network":[45],"based":[46],"generalized":[47],"eigenvalue":[48],"beamformer":[49,58,90],"and":[50,116,130],"application-specific":[51,86],"model":[52],"allows":[54,117],"for":[55],"optimization":[56],"w.r.t.":[59],"target":[60],"application.":[61],"our":[63,104],"case,":[64],"application":[66],"speaker":[68,73],"verification":[69],"which":[70,112],"utilizes":[71],"embedding":[74],"(x-vector)":[75],"extractor":[76],"conveniently":[78],"comes":[79],"desired":[81],"loss.":[82],"We":[83,102],"show":[84],"brings":[91],"performance":[92],"improvements":[93],"over":[94],"system":[96],"trained":[97],"in":[98],"standard":[100],"way.":[101],"perform":[103],"analysis":[105],"on":[106],"recently":[108],"introduced":[109],"VOiCES":[110],"corpus":[111],"contains":[113],"multichannel":[114],"data":[115],"us":[118],"modify":[120],"evaluation":[122],"trials":[123],"such":[124],"enrollment":[126],"recordings":[127],"remain":[128],"single-channel":[129],"test":[131],"utterances":[132],"are":[133],"multichannel.":[134]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}