{"id":"https://openalex.org/W2586796625","doi":"https://doi.org/10.1109/slt.2016.7846284","title":"Unsupervised k-means clustering based out-of-set candidate selection for robust open-set language recognition","display_name":"Unsupervised k-means clustering based out-of-set candidate selection for robust open-set language recognition","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2586796625","doi":"https://doi.org/10.1109/slt.2016.7846284","mag":"2586796625"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846284","doi":"https://doi.org/10.1109/slt.2016.7846284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846284","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"volume":null,"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/A5115603610","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0001-5975-9781","observed_orcids":["https://orcid.org/0000-0001-5975-9781","https://orcid.org/0009-0009-0048-8951","https://orcid.org/0009-0002-3020-8331","https://orcid.org/0009-0005-2936-0696"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.1796,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50965983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"324","last_page":"329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0006000000284984708,"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/T10860","display_name":"Speech and Audio Processing","score":0.0005000000237487257,"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/i-vectors","display_name":"i-vectors","score":0.6480000019073486},{"id":"https://openalex.org/keywords/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.7200000286102295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540148496627808},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6931208968162537},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6114916205406189},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5626747608184814},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5584688186645508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5311784744262695},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5250261425971985},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.44606414437294006},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4046744704246521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3422333598136902},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25232070684432983},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2016.7846284","doi":"https://doi.org/10.1109/slt.2016.7846284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846284","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W135246240","https://openalex.org/W151003953","https://openalex.org/W645179519","https://openalex.org/W1490504384","https://openalex.org/W1968377371","https://openalex.org/W1968652492","https://openalex.org/W2011142564","https://openalex.org/W2011430131","https://openalex.org/W2039057510","https://openalex.org/W2045801524","https://openalex.org/W2056119007","https://openalex.org/W2095501777","https://openalex.org/W2107638917","https://openalex.org/W2112582577","https://openalex.org/W2113832997","https://openalex.org/W2121415728","https://openalex.org/W2128952115","https://openalex.org/W2136879537","https://openalex.org/W2148913638","https://openalex.org/W2150769028","https://openalex.org/W2153410846","https://openalex.org/W2172287020","https://openalex.org/W2189248916","https://openalex.org/W2340176088","https://openalex.org/W2505434962","https://openalex.org/W2549762342","https://openalex.org/W2763651403","https://openalex.org/W6606123296"],"related_works":["https://openalex.org/W2784561952","https://openalex.org/W1968377371","https://openalex.org/W2501121137","https://openalex.org/W2790446349","https://openalex.org/W2128952115","https://openalex.org/W4386302218","https://openalex.org/W4281493663","https://openalex.org/W2737837613","https://openalex.org/W2406366455","https://openalex.org/W1542720960"],"abstract_inverted_index":{"Research":[0],"in":[1,29],"open-set":[2],"language":[3,12,18,44,67,98,185],"identification":[4],"(LID)":[5],"generally":[6],"focuses":[7],"more":[8],"on":[9,117,150],"accurate":[10],"in-set":[11,36],"modeling":[13],"versus":[14,34],"improved":[15],"out-of-set":[16],"(OOS)":[17],"rejection.":[19],"The":[20,157],"main":[21],"reason":[22],"for":[23,64,81,108,164],"this":[24,51],"is":[25,46,106,115],"the":[26,35,83,95,131,135,169,176],"increased":[27],"cost/resources":[28],"collecting":[30],"sufficient":[31],"OOS":[32,43,60,66,97,110,137,152,184],"data,":[33],"languages":[37],"of":[38,178,183],"interest.":[39],"Therefore,":[40,100,168],"unknown":[41],"or":[42],"rejection":[45,153],"a":[47,58,118,122,180],"challenge.":[48],"To":[49],"address":[50],"through":[52],"efficient":[53],"data":[54,166],"collection,":[55],"we":[56],"propose":[57],"flexible":[59],"candidate":[61,111],"selection":[62,133],"method":[63,114,159],"universal":[65],"coverage.":[68],"Since":[69],"state-of-the-art":[70],"i-vector":[71],"system":[72],"followed":[73],"by":[74,143],"generative":[75],"Gaussian":[76],"back-end":[77],"achieves":[78,172],"effective":[79,109],"performance":[80,149,174],"LID,":[82],"selected":[84],"K":[85],"candidates":[86,186],"are":[87],"expected":[88],"to":[89,93],"be":[90,141],"general":[91],"enough":[92],"represent":[94],"entire":[96],"space.":[99],"an":[101],"unsupervised":[102],"k-means":[103],"clustering":[104],"approach":[105],"proposed":[107,132,158,170],"selection.":[112],"This":[113],"evaluated":[116],"dataset":[119],"derived":[120],"from":[121],"large-scale":[123],"corpus":[124],"(LRE-09)":[125],"which":[126],"contains":[127],"40":[128],"languages.":[129],"With":[130],"method,":[134],"total":[136],"training":[138],"diversity":[139],"can":[140],"reduced":[142],"89%":[144],"and":[145,154],"still":[146],"achieve":[147],"better":[148],"both":[151],"overall":[155],"classification.":[156],"also":[160],"shows":[161],"clear":[162],"benefits":[163],"greater":[165],"enhancement.":[167],"solution":[171],"sustained":[173],"with":[175],"advantage":[177],"employing":[179],"minimum":[181],"number":[182],"efficiently.":[187]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2017-02-17T00:00:00"}