{"id":"https://openalex.org/W3160945063","doi":"https://doi.org/10.1109/icassp39728.2021.9414725","title":"Analysis of X-Vectors for Low-Resource Speech Recognition","display_name":"Analysis of X-Vectors for Low-Resource Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160945063","doi":"https://doi.org/10.1109/icassp39728.2021.9414725","mag":"3160945063"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5065253688","display_name":"Martin Karafi\u00e1t","orcid":"https://orcid.org/0000-0001-6474-8366"},"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":"Martin Karafiat","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"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/A5045351360","display_name":"Karel Vesel\u00fd","orcid":"https://orcid.org/0000-0002-3568-7493"},"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":"Karel Vesely","raw_affiliation_strings":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"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/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":["Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"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/A5054937420","display_name":"J\u00e1n Profant","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110967","display_name":"Phonexia (Czechia)","ror":"https://ror.org/01q216d88","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210110967"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Profant","raw_affiliation_strings":["Phonexia s.r.o, Brno, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonexia s.r.o, Brno, Czechia","institution_ids":["https://openalex.org/I4210110967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026807880","display_name":"Jiri Nytra","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110967","display_name":"Phonexia (Czechia)","ror":"https://ror.org/01q216d88","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210110967"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jiri Nytra","raw_affiliation_strings":["Phonexia s.r.o, Brno, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonexia s.r.o, Brno, Czechia","institution_ids":["https://openalex.org/I4210110967"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038969682","display_name":"Miroslav Hlav\u00e1\u010dek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110967","display_name":"Phonexia (Czechia)","ror":"https://ror.org/01q216d88","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210110967"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Miroslav Hlavacek","raw_affiliation_strings":["Phonexia s.r.o, Brno, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonexia s.r.o, Brno, Czechia","institution_ids":["https://openalex.org/I4210110967"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078840047","display_name":"Tom\u00e1\u0161 Pavl\u0131\u0301\u010dek","orcid":"https://orcid.org/0000-0003-2581-2657"},"institutions":[{"id":"https://openalex.org/I4210110967","display_name":"Phonexia (Czechia)","ror":"https://ror.org/01q216d88","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210110967"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Tomas Pavlicek","raw_affiliation_strings":["Phonexia s.r.o, Brno, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonexia s.r.o, Brno, Czechia","institution_ids":["https://openalex.org/I4210110967"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6997,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75711112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6998","last_page":"7002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9975000023841858,"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":0.7583925127983093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7302177548408508},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5591379404067993},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5217885971069336},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4683600962162018},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.45640623569488525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44141268730163574},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.432122141122818},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41513895988464355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40938496589660645},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35743916034698486},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.08076250553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583925127983093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7302177548408508},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5591379404067993},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5217885971069336},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4683600962162018},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.45640623569488525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44141268730163574},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.432122141122818},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41513895988464355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40938496589660645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35743916034698486},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.08076250553131104},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/icassp39728.2021.9414725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W2079623482","https://openalex.org/W2094147890","https://openalex.org/W2106554350","https://openalex.org/W2131342762","https://openalex.org/W2150769028","https://openalex.org/W2164240571","https://openalex.org/W2276408190","https://openalex.org/W2404568753","https://openalex.org/W2407922671","https://openalex.org/W2474824677","https://openalex.org/W2514741789","https://openalex.org/W2514966966","https://openalex.org/W2746887616","https://openalex.org/W2888867175","https://openalex.org/W2890964092","https://openalex.org/W2972392008","https://openalex.org/W2991951409","https://openalex.org/W3007327651","https://openalex.org/W3044481399","https://openalex.org/W4308252168","https://openalex.org/W6631362777","https://openalex.org/W6713570806","https://openalex.org/W6720877245","https://openalex.org/W6771538394"],"related_works":["https://openalex.org/W4389670110","https://openalex.org/W2187546663","https://openalex.org/W2429057255","https://openalex.org/W148745890","https://openalex.org/W2611942503","https://openalex.org/W2899790217","https://openalex.org/W1576092969","https://openalex.org/W2053269318","https://openalex.org/W4315621326","https://openalex.org/W2380970022"],"abstract_inverted_index":{"The":[0],"paper":[1],"presents":[2],"a":[3],"study":[4],"of":[5,7,11,51],"usability":[6],"x-vectors":[8,77],"for":[9,46,60],"adaptation":[10],"automatic":[12],"speech":[13],"recognition":[14,28],"(ASR)":[15],"systems.":[16],"X-vectors":[17],"are":[18],"Neural":[19],"Network":[20],"(NN)-based":[21],"speaker":[22,27],"embeddings":[23],"recently":[24],"proposed":[25],"in":[26],"(SR).":[29],"They":[30],"quickly":[31],"replaced":[32],"common":[33],"i-vectors":[34],"and":[35],"became":[36],"new":[37],"state-of-the-art":[38],"technique.":[39],"Here,":[40],"the":[41,49,61,83],"same":[42],"approach":[43],"is":[44],"adopted":[45],"ASR":[47,59],"with":[48,76],"hope":[50],"similar":[52],"outcome.":[53],"All":[54],"experiments":[55],"were":[56],"done":[57],"on":[58,67,89],"latest":[62],"IARPA":[63],"MATERIAL":[64],"evaluation":[65],"running":[66],"Pashto":[68,91],"language.":[69],"Over":[70],"1%":[71],"absolute":[72],"improvement":[73],"was":[74,86],"observed":[75],"over":[78],"traditional":[79],"i-vectors,":[80],"even":[81],"when":[82],"x-vector":[84],"extractor":[85],"not":[87],"trained":[88],"target":[90],"data.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
