{"id":"https://openalex.org/W2133628825","doi":"https://doi.org/10.1109/asru.2007.4430087","title":"Two extensions to ensemble speaker and speaking environment modeling for robust automatic speech recognition","display_name":"Two extensions to ensemble speaker and speaking environment modeling for robust automatic speech recognition","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2133628825","doi":"https://doi.org/10.1109/asru.2007.4430087","mag":"2133628825"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"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":true,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, USA","Georgia Institute of Technology , Atlanta#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology , Atlanta#TAB#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111937761","display_name":"Chin-Hui Lee","orcid":null},"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, USA","Georgia Institute of Technology , Atlanta#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology , Atlanta#TAB#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044008055"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":2.3467,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90125245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"80"},"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":0.9997000098228455,"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":0.9980999827384949,"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":0.724082350730896},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6998862028121948},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6635782122612},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.652524471282959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5609844326972961},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5561041235923767},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5340731739997864},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5280790328979492},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.4603644609451294},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4589546322822571},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.43790847063064575},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.42192861437797546},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.41647815704345703},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.4101327657699585},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17377540469169617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724082350730896},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6998862028121948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6635782122612},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.652524471282959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5609844326972961},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5561041235923767},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5340731739997864},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5280790328979492},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.4603644609451294},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4589546322822571},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.43790847063064575},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.42192861437797546},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.41647815704345703},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.4101327657699585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17377540469169617},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W26894416","https://openalex.org/W33099690","https://openalex.org/W63876021","https://openalex.org/W1517348348","https://openalex.org/W2051203581","https://openalex.org/W2082474452","https://openalex.org/W2100969003","https://openalex.org/W2140977001","https://openalex.org/W2146871184","https://openalex.org/W2151484683","https://openalex.org/W2158289097","https://openalex.org/W4237826793","https://openalex.org/W6601069994","https://openalex.org/W6601380903","https://openalex.org/W6602550718","https://openalex.org/W6630687167"],"related_works":["https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366","https://openalex.org/W2181956362","https://openalex.org/W2148323604","https://openalex.org/W2914064142"],"abstract_inverted_index":{"Recently":[0],"an":[1,60,110],"ensemble":[2,65,81,91],"speaker":[3],"and":[4,83],"speaking":[5],"environment":[6,22,55],"modeling":[7],"(ESSEM)":[8],"approach":[9],"to":[10,78,88,98,117],"characterizing":[11],"unknown":[12],"testing":[13,54],"environments":[14],"was":[15],"studied":[16],"for":[17,45,51],"robust":[18],"speech":[19],"recognition.":[20],"Each":[21],"is":[23,56],"modeled":[24],"by":[25,59],"a":[26,41,46,52,72,84,103,128],"super-vector":[27,50,85],"consisting":[28],"of":[29,33,40,43,113],"the":[30,64,133,142,147,150],"entire":[31],"set":[32,42],"mean":[34],"vectors":[35],"from":[36,115],"all":[37],"Gaussian":[38],"densities":[39],"HMMs":[44],"particular":[47],"environment.":[48],"The":[49],"new":[53],"then":[57],"obtained":[58,131],"affine":[61],"transformation":[62],"on":[63,100,149],"super-vectors.":[66],"In":[67,102],"this":[68,140],"paper,":[69],"we":[70,108],"propose":[71],"minimum":[73],"classification":[74],"error":[75],"training":[76],"procedure":[77],"obtain":[79],"discriminative":[80],"elements,":[82],"clustering":[86],"technique":[87],"achieve":[89],"refined":[90],"structures.":[92],"We":[93],"test":[94],"these":[95,122],"two":[96,123],"extentions":[97,124],"ESSEM":[99],"Aurora2.":[101],"per-utterance":[104],"unsupervised":[105],"adaptation":[106],"mode":[107],"achieved":[109],"average":[111],"WER":[112,130],"4.99%":[114],"OdB":[116],"20":[118],"dB":[119],"conditions":[120],"with":[121,127,132],"when":[125],"compared":[126],"5.51%":[129],"ML-trained":[134],"gender-dependent":[135],"baseline.":[136],"To":[137],"our":[138],"knowledge":[139],"represents":[141],"best":[143],"result":[144],"reported":[145],"in":[146],"literature":[148],"Aurora2":[151],"connected":[152],"digit":[153],"recognition":[154],"task.":[155]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}