{"id":"https://openalex.org/W2131708681","doi":"https://doi.org/10.1109/asru.2009.5373236","title":"MAP estimation of online mapping parameters in ensemble speaker and speaking environment modeling","display_name":"MAP estimation of online mapping parameters in ensemble speaker and speaking environment modeling","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2131708681","doi":"https://doi.org/10.1109/asru.2009.5373236","mag":"2131708681"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/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":true,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Spoken Language Communication Group, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Communication Group, National Institute of Information and Communications Technology, Kyoto, 619-0288, Japan"],"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 Communication Group, National Institute of Information and Communications Technology, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077037266","display_name":"Shigeki Matsuda","orcid":null},"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":"Shigeki Matsuda","raw_affiliation_strings":["Spoken Language Communication Group, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Communication Group, National Institute of Information and Communications Technology, Kyoto, 619-0288, Japan"],"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 Communication Group, National Institute of Information and Communications Technology, Kyoto, 619-0288, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"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":"Satoshi Nakamura","raw_affiliation_strings":["Spoken Language Communication Group, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Communication Group, National Institute of Information and Communications Technology, Kyoto, 619-0288, Japan"],"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 Communication Group, National Institute of Information and Communications Technology, Kyoto, 619-0288, Japan","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 and Computer Engineering Georgia Institute of Technology Atlanta GA 30332-0250 USA"],"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 and Computer Engineering Georgia Institute of Technology Atlanta GA 30332-0250 USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044008055"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.8724,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80884293,"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":"271","last_page":"275"},"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":0.9998999834060669,"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":0.9986000061035156,"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/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.8727253675460815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7170670032501221},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5092033743858337},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4807724356651306},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.47945988178253174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4679718613624573},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4466795027256012},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4456164836883545},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.43243294954299927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4288310408592224},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4249917268753052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4209875166416168},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4207969307899475},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.3669168949127197},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1834309995174408},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17376470565795898},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1528608798980713}],"concepts":[{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.8727253675460815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7170670032501221},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5092033743858337},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4807724356651306},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.47945988178253174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4679718613624573},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4466795027256012},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4456164836883545},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.43243294954299927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4288310408592224},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4249917268753052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4209875166416168},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4207969307899475},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.3669168949127197},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1834309995174408},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17376470565795898},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1528608798980713},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373236","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W26894416","https://openalex.org/W117579468","https://openalex.org/W1509129286","https://openalex.org/W1517348348","https://openalex.org/W1585396714","https://openalex.org/W1979141632","https://openalex.org/W2049633694","https://openalex.org/W2076507042","https://openalex.org/W2081976287","https://openalex.org/W2082474452","https://openalex.org/W2094709280","https://openalex.org/W2100969003","https://openalex.org/W2103537425","https://openalex.org/W2138534187","https://openalex.org/W2141930065","https://openalex.org/W2146871184","https://openalex.org/W2149175990","https://openalex.org/W2157178676","https://openalex.org/W2158289097","https://openalex.org/W2159112514","https://openalex.org/W2160373860","https://openalex.org/W2165108269","https://openalex.org/W2308181013","https://openalex.org/W6630687167","https://openalex.org/W6680790744"],"related_works":["https://openalex.org/W1503532423","https://openalex.org/W2150865841","https://openalex.org/W1967494390","https://openalex.org/W2138865713","https://openalex.org/W3013496002","https://openalex.org/W2465363361","https://openalex.org/W2896820906","https://openalex.org/W4284711868","https://openalex.org/W2101542441","https://openalex.org/W2021166481"],"abstract_inverted_index":{"Recently,":[0],"an":[1],"ensemble":[2],"speaker":[3],"and":[4,118],"speaking":[5],"environment":[6,29,47,101],"modeling":[7],"(ESSEM)":[8],"framework":[9],"was":[10],"proposed":[11],"to":[12,37,76,84,89,150,162,173,179],"enhance":[13],"automatic":[14],"speech":[15],"recognition":[16],"performance":[17,139],"under":[18,144],"adverse":[19],"conditions.":[20,147],"In":[21,53,71],"the":[22,27,32,44,54,58,86,98,104,125,155,183],"online":[23],"phase":[24],"of":[25,40,100,112,131,176],"ESSEM,":[26,142],"prepared":[28],"structure":[30],"in":[31,121,168],"offline":[33],"stage":[34],"is":[35],"transformed":[36],"a":[38,50,66,78,80,91,159,171],"set":[39],"acoustic":[41],"models":[42],"for":[43],"target":[45],"testing":[46,185],"by":[48],"using":[49,128],"mapping":[51,59,87],"function.":[52],"original":[55],"ESSEM":[56,135,157],"framework,":[57],"function":[60,88],"parameters":[61],"are":[62],"estimated":[63],"based":[64],"on":[65],"maximum":[67,79],"likelihood":[68],"(ML)":[69],"criterion.":[70],"this":[72,122],"study,":[73],"we":[74,107],"propose":[75],"use":[77],"posteriori":[81],"(MAP)":[82],"criterion":[83],"calculate":[85],"avoid":[90],"possible":[92],"over-fitting":[93],"problem":[94],"that":[95],"can":[96,136],"degrade":[97],"accuracy":[99],"characterization.":[102],"For":[103],"MAP":[105],"estimation,":[106],"also":[108],"study":[109],"two":[110],"types":[111],"prior":[113,117,132],"densities,":[114,133],"namely,":[115],"clustered":[116],"hierarchical":[119],"prior,":[120],"paper.":[123],"On":[124],"Aurora-2":[126],"task":[127],"either":[129],"type":[130],"MAP-based":[134,156],"achieve":[137],"better":[138],"than":[140],"ML-based":[141],"especially":[143],"low":[145],"SNR":[146],"When":[148],"comparing":[149],"our":[151],"best":[152],"baseline":[153],"results,":[154],"achieves":[158],"14.97%":[160],"(5.41%":[161],"4.60%)":[163],"word":[164],"error":[165],"rate":[166],"reduction":[167],"average":[169],"at":[170],"signal":[172],"noise":[174],"ratio":[175],"0":[177],"dB":[178,181],"20":[180],"over":[182],"three":[184],"sets.":[186]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}