{"id":"https://openalex.org/W2103537425","doi":"https://doi.org/10.1109/tasl.2009.2016231","title":"An Ensemble Speaker and Speaking Environment Modeling Approach to Robust Speech Recognition","display_name":"An Ensemble Speaker and Speaking Environment Modeling Approach to Robust Speech Recognition","publication_year":2009,"publication_date":"2009-06-16","ids":{"openalex":"https://openalex.org/W2103537425","doi":"https://doi.org/10.1109/tasl.2009.2016231","mag":"2103537425"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2016231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2016231","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Spoken Language Communication Group, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Commun. Group, Nat. Inst. of Inf. & Commun. Technol., Seika"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Group, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Spoken Language Commun. Group, Nat. Inst. of Inf. & Commun. Technol., Seika","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","[School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA]","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.662,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96672464,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"17","issue":"5","first_page":"1025","last_page":"1037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9998000264167786,"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/speech-recognition","display_name":"Speech recognition","score":0.7003216743469238},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5930167436599731},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5634445548057556}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7003216743469238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5930167436599731},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5634445548057556}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2009.2016231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2016231","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:smartech.gatech.edu:1853/26540","is_oa":false,"landing_page_url":"http://hdl.handle.net/1853/26540","pdf_url":null,"source":{"id":"https://openalex.org/S4377196313","display_name":"SMARTech Repository (Georgia Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130701444","host_organization_name":"Georgia Institute of Technology","host_organization_lineage":["https://openalex.org/I130701444"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dissertation"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568},{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":119,"referenced_works":["https://openalex.org/W26894416","https://openalex.org/W33099690","https://openalex.org/W46190896","https://openalex.org/W63876021","https://openalex.org/W110305337","https://openalex.org/W167743276","https://openalex.org/W188247790","https://openalex.org/W194267938","https://openalex.org/W321662557","https://openalex.org/W1501633760","https://openalex.org/W1508165687","https://openalex.org/W1509129286","https://openalex.org/W1517348348","https://openalex.org/W1519203663","https://openalex.org/W1537685344","https://openalex.org/W1560013842","https://openalex.org/W1573570773","https://openalex.org/W1585396714","https://openalex.org/W1586170454","https://openalex.org/W1599512239","https://openalex.org/W1966013632","https://openalex.org/W1967558850","https://openalex.org/W1974218343","https://openalex.org/W1977434607","https://openalex.org/W1979141632","https://openalex.org/W1980800561","https://openalex.org/W1986931325","https://openalex.org/W1993259959","https://openalex.org/W2002087363","https://openalex.org/W2002342963","https://openalex.org/W2007861821","https://openalex.org/W2011077222","https://openalex.org/W2033565080","https://openalex.org/W2047769394","https://openalex.org/W2049633694","https://openalex.org/W2050693797","https://openalex.org/W2058216438","https://openalex.org/W2069631319","https://openalex.org/W2069976350","https://openalex.org/W2073738917","https://openalex.org/W2073936352","https://openalex.org/W2076507042","https://openalex.org/W2079076391","https://openalex.org/W2082474452","https://openalex.org/W2084444178","https://openalex.org/W2086267546","https://openalex.org/W2090861223","https://openalex.org/W2094709280","https://openalex.org/W2097685957","https://openalex.org/W2098692363","https://openalex.org/W2100969003","https://openalex.org/W2110467295","https://openalex.org/W2111479622","https://openalex.org/W2113981416","https://openalex.org/W2114548037","https://openalex.org/W2115415333","https://openalex.org/W2116196769","https://openalex.org/W2121178390","https://openalex.org/W2121415090","https://openalex.org/W2125838338","https://openalex.org/W2128653836","https://openalex.org/W2129087637","https://openalex.org/W2130266733","https://openalex.org/W2133628825","https://openalex.org/W2135704565","https://openalex.org/W2136386449","https://openalex.org/W2136389896","https://openalex.org/W2136439176","https://openalex.org/W2137401359","https://openalex.org/W2138534187","https://openalex.org/W2139801919","https://openalex.org/W2140498480","https://openalex.org/W2140977001","https://openalex.org/W2141934504","https://openalex.org/W2145284369","https://openalex.org/W2146871184","https://openalex.org/W2148154194","https://openalex.org/W2148694408","https://openalex.org/W2149097237","https://openalex.org/W2149175990","https://openalex.org/W2149310755","https://openalex.org/W2150907703","https://openalex.org/W2151484683","https://openalex.org/W2151693816","https://openalex.org/W2152131029","https://openalex.org/W2155368638","https://openalex.org/W2156447271","https://openalex.org/W2156909104","https://openalex.org/W2157178676","https://openalex.org/W2157590573","https://openalex.org/W2158289097","https://openalex.org/W2159112514","https://openalex.org/W2160373860","https://openalex.org/W2161562001","https://openalex.org/W2163314930","https://openalex.org/W2164512012","https://openalex.org/W2165108269","https://openalex.org/W2165606141","https://openalex.org/W2167057710","https://openalex.org/W2167152389","https://openalex.org/W2170120894","https://openalex.org/W2172200851","https://openalex.org/W2182212465","https://openalex.org/W2213215029","https://openalex.org/W2294690908","https://openalex.org/W2308181013","https://openalex.org/W2338891360","https://openalex.org/W2559758445","https://openalex.org/W2799061466","https://openalex.org/W2949468472","https://openalex.org/W3127686677","https://openalex.org/W3149335959","https://openalex.org/W4244494905","https://openalex.org/W6602550718","https://openalex.org/W6630687167","https://openalex.org/W6634340323","https://openalex.org/W6644042397","https://openalex.org/W6685110083","https://openalex.org/W6697419950"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2499802997","https://openalex.org/W3162054169","https://openalex.org/W2893763841","https://openalex.org/W2312116756","https://openalex.org/W2778699561"],"abstract_inverted_index":{"We":[0,135,174],"propose":[1,151],"an":[2,45,227,232],"ensemble":[3,46,91,171],"speaker":[4,47],"and":[5,36,48,125,140,164],"speaking":[6,49],"environment":[7,50,92,107,129,138,146,162,172,214,228],"modeling":[8],"(ESSEM)":[9],"approach":[10],"to":[11,16,143,158],"characterizing":[12],"environments":[13],"in":[14,95,131],"order":[15],"enhance":[17,159],"performance":[18,204,225],"robustness":[19],"of":[20,56,61,65,73,76,127,169,205,234],"automatic":[21],"speech":[22],"recognition":[23,185],"systems":[24],"under":[25],"adverse":[26],"conditions.":[27],"The":[28],"ESSEM":[29,178,191,206,220],"process":[30],"comprises":[31],"two":[32],"phases,":[33],"the":[34,37,40,62,69,86,90,96,101,123,128,132,145,167,170,176,181,203,222],"offline":[35,41,97,133],"online.":[38],"In":[39,85,114],"phase,":[42,88,98],"we":[43,99,117,150,217],"prepare":[44],"space":[51,93,130,147,229],"formed":[52],"by":[53,211,231],"a":[54,74,82,104,110,152,196],"collection":[55],"super-vectors.":[57],"Each":[58],"super-vector":[59,102],"consists":[60],"entire":[63],"set":[64,75],"means":[66],"from":[67],"all":[68,235],"Gaussian":[70],"mixture":[71],"components":[72],"hidden":[77],"Markov":[78],"models":[79],"that":[80,190,219],"characterizes":[81],"particular":[83],"environment.":[84],"online":[87],"with":[89,226],"prepared":[94],"estimate":[100],"for":[103,121],"new":[105],"testing":[106],"based":[108],"on":[109,119,180],"stochastic":[111],"matching":[112],"criterion.":[113],"this":[115],"paper,":[116],"focus":[118],"methods":[120],"enhancing":[122],"construction":[124],"coverage":[126,168],"phase.":[134],"first":[136],"demonstrate":[137],"clustering":[139],"partitioning":[141],"algorithms":[142],"structure":[144],"well;":[148],"then,":[149],"minimum":[153],"classification":[154],"error":[155],"training":[156],"algorithm":[157],"discrimination":[160],"across":[161],"super-vectors":[163],"therefore":[165],"broaden":[166],"space.":[173],"evaluate":[175],"proposed":[177],"framework":[179],"Aurora2":[182],"connected":[183],"digit":[184],"task.":[186],"Experimental":[187],"results":[188],"verify":[189],"provides":[192],"clear":[193],"improvement":[194],"over":[195],"baseline":[197],"system":[198],"without":[199],"environmental":[200],"compensation.":[201],"Moreover,":[202],"can":[207],"be":[208],"further":[209],"enhanced":[210],"using":[212],"well-structured":[213],"spaces.":[215],"Finally,":[216],"confirm":[218],"gives":[221],"best":[223],"overall":[224],"refined":[230],"integration":[233],"techniques.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}