{"id":"https://openalex.org/W2067373094","doi":"https://doi.org/10.2298/csis120208053f","title":"Speech unit category based short utterance speaker recognition","display_name":"Speech unit category based short utterance speaker recognition","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2067373094","doi":"https://doi.org/10.2298/csis120208053f","mag":"2067373094"},"language":"en","primary_location":{"id":"doi:10.2298/csis120208053f","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis120208053f","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141200053F","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141200053F","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004628748","display_name":"Nakhat Fatima","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nakhat Fatima","raw_affiliation_strings":["Center for Speech and Language Technologies, Division of Technical Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technical Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060120730","display_name":"Xiaojun Wu","orcid":"https://orcid.org/0000-0002-8519-104X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Wu","raw_affiliation_strings":["Center for Speech and Language Technologies, Division of Technical Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technical Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041679034","display_name":"Fang Zheng","orcid":"https://orcid.org/0000-0002-7858-4080"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Zheng","raw_affiliation_strings":["Center for Speech and Language Technologies, Division of Technical Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Division of Technical Innovation and Development, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.10308826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":"4","first_page":"1407","last_page":"1430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9930999875068665,"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":0.9527000188827515,"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":0.8467041254043579},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8449387550354004},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8287128210067749},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5431659817695618},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.48745250701904297},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.46809151768684387},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46156778931617737},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4602891206741333},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.42179208993911743},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34350818395614624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33838731050491333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467041254043579},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8449387550354004},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8287128210067749},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5431659817695618},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.48745250701904297},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.46809151768684387},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46156778931617737},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4602891206741333},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.42179208993911743},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34350818395614624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33838731050491333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.2298/csis120208053f","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis120208053f","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141200053F","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:doiserbia:1820-02141200053F","is_oa":false,"landing_page_url":"http://doi.org/10.2298/CSIS120208053F","pdf_url":null,"source":{"id":"https://openalex.org/S4306400515","display_name":"Digital Object Identifier (DOI) Repository Serbia (National Library of Serbia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210142455","host_organization_name":"National Library of Serbia","host_organization_lineage":["https://openalex.org/I4210142455"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":". 9(4) 1407-1430"}],"best_oa_location":{"id":"doi:10.2298/csis120208053f","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis120208053f","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02141200053F","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Science and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G1828425977","display_name":null,"funder_award_id":"973 Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G465702083","display_name":null,"funder_award_id":"2013CB329302","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8204283577","display_name":"\u8bf4\u8bdd\u4eba\u8bc6\u522b\u4e2d\u65f6\u53d8\u9c81\u68d2\u7684\u58f0\u7eb9\u7279\u5f81\u7814\u7a76","funder_award_id":"61271389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2067373094.pdf","grobid_xml":"https://content.openalex.org/works/W2067373094.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W67277430","https://openalex.org/W82466267","https://openalex.org/W112821631","https://openalex.org/W131170453","https://openalex.org/W154652619","https://openalex.org/W181595617","https://openalex.org/W2015919351","https://openalex.org/W2076521541","https://openalex.org/W2091220214","https://openalex.org/W2095605110","https://openalex.org/W2105393821","https://openalex.org/W2106292168","https://openalex.org/W2119979862","https://openalex.org/W2121415728","https://openalex.org/W2154278880","https://openalex.org/W2155741089","https://openalex.org/W2183001115","https://openalex.org/W2352683462","https://openalex.org/W2357242099","https://openalex.org/W2383388535","https://openalex.org/W2612380871","https://openalex.org/W3037288542","https://openalex.org/W6674000675"],"related_works":["https://openalex.org/W2379338161","https://openalex.org/W2083125711","https://openalex.org/W2354951577","https://openalex.org/W2024527724","https://openalex.org/W2389094966","https://openalex.org/W2106571394","https://openalex.org/W6375046","https://openalex.org/W2355736622","https://openalex.org/W2076031771","https://openalex.org/W2371012917"],"abstract_inverted_index":{"Information":[0],"of":[1,13,44,60,65,79,103,182,189,197],"speech":[2,38,61,81,94,125,146,156],"units":[3,62,67,95],"like":[4],"vowels,":[5],"consonants":[6],"and":[7,110,115,153,184,191],"syllables":[8],"can":[9],"be":[10,70],"a":[11,24,77,122,175],"kind":[12],"knowledge":[14],"used":[15,137],"in":[16,23,28,149,165],"text-independent":[17],"Short":[18],"Utterance":[19],"Speaker":[20],"Recognition":[21],"(SUSR)":[22],"similar":[25,93],"way":[26],"as":[27,121],"text-dependent":[29],"speaker":[30,160],"recognition.":[31],"In":[32],"such":[33],"tasks,":[34],"data":[35],"for":[36,90,144,194],"each":[37,145],"unit,":[39],"especially":[40],"at":[41],"the":[42,57,66,101,150,202],"time":[43],"recognition,":[45,161],"is":[46,52,88,127],"often":[47],"not":[48,53,69],"enough.":[49],"Hence,":[50],"it":[51],"practical":[54],"to":[55,138,154],"use":[56],"full":[58],"set":[59],"because":[63],"some":[64],"might":[68],"well":[71],"trained.":[72],"To":[73],"solve":[74],"this":[75],"problem,":[76],"method":[78],"using":[80],"unit":[82,147,157],"categories":[83],"rather":[84],"than":[85],"individual":[86],"phones":[87],"proposed":[89],"SUSR,":[91],"wherein":[92],"are":[96,136],"put":[97],"together,":[98],"hence":[99],"solving":[100],"problem":[102],"sparse":[104],"data.":[105],"We":[106],"define":[107],"Vowel,":[108],"Consonant,":[109],"Syllable":[111],"Categories":[112],"(VC,":[113],"CC":[114,131],"SC)":[116],"with":[117,201],"Standard":[118],"Chinese":[119],"(Putonghua)":[120],"reference.":[123],"A":[124],"utterance":[126,199],"recognized":[128],"into":[129],"VC,":[130],"ad":[132],"SC":[133],"sequences":[134],"which":[135],"train":[139],"Universal":[140],"Background":[141,169],"Models":[142],"(UBM)":[143],"category":[148,158],"training":[151],"procedure,":[152],"perform":[155],"dependent":[159],"respectively.":[162],"Experimental":[163],"results":[164],"Gaussian":[166],"Mixture":[167],"Model-Universal":[168],"Model":[170],"(GMM-UBM)":[171],"based":[172],"system":[173],"give":[174],"relative":[176],"equal":[177],"error":[178],"rate":[179],"(EER)":[180],"reduction":[181],"54.50%":[183],"40.95%":[185],"from":[186],"minimum":[187],"EERs":[188],"VCs":[190],"SCs,":[192],"respectively,":[193],"2":[195],"seconds":[196],"test":[198],"compared":[200],"existing":[203],"SUSR":[204],"systems.":[205]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2016-06-24T00:00:00"}