{"id":"https://openalex.org/W2036155843","doi":"https://doi.org/10.1109/tasl.2010.2091633","title":"A Novel Mask Estimation Method Employing Posterior-Based Representative Mean Estimate for Missing-Feature Speech Recognition","display_name":"A Novel Mask Estimation Method Employing Posterior-Based Representative Mean Estimate for Missing-Feature Speech Recognition","publication_year":2011,"publication_date":"2011-05-13","ids":{"openalex":"https://openalex.org/W2036155843","doi":"https://doi.org/10.1109/tasl.2010.2091633","mag":"2036155843"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2091633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2091633","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/A5101977971","display_name":"Wooil Kim","orcid":"https://orcid.org/0000-0002-6075-570X"},"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":true,"raw_author_name":"Wooil Kim","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#","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"},"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), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101977971"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.4498,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89433761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"5","first_page":"1434","last_page":"1443"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.6756333708763123},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6186683773994446},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5326617956161499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5240783095359802},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5049510598182678},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.48801031708717346},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4794548749923706},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.45299267768859863},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4486897587776184},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42848819494247437},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.29263952374458313},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.12660491466522217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6756333708763123},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6186683773994446},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5326617956161499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5240783095359802},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5049510598182678},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.48801031708717346},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4794548749923706},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.45299267768859863},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4486897587776184},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42848819494247437},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.29263952374458313},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.12660491466522217},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2091633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2091633","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W26240804","https://openalex.org/W65880231","https://openalex.org/W79317937","https://openalex.org/W157345740","https://openalex.org/W289804034","https://openalex.org/W346849789","https://openalex.org/W427469064","https://openalex.org/W1974387177","https://openalex.org/W2010354808","https://openalex.org/W2017452035","https://openalex.org/W2045036776","https://openalex.org/W2072328708","https://openalex.org/W2074354966","https://openalex.org/W2086139506","https://openalex.org/W2093985521","https://openalex.org/W2100969003","https://openalex.org/W2104212264","https://openalex.org/W2115737782","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2129204992","https://openalex.org/W2130283666","https://openalex.org/W2131118736","https://openalex.org/W2134958651","https://openalex.org/W2142193238","https://openalex.org/W2143855671","https://openalex.org/W2146083413","https://openalex.org/W2146871184","https://openalex.org/W2147287194","https://openalex.org/W2150866759","https://openalex.org/W2151484683","https://openalex.org/W2154912038","https://openalex.org/W2158047270","https://openalex.org/W2162213734","https://openalex.org/W2163008623","https://openalex.org/W2164388284","https://openalex.org/W2167204516","https://openalex.org/W2792905612","https://openalex.org/W3147539069","https://openalex.org/W6603280604","https://openalex.org/W6606419009","https://openalex.org/W6679498742","https://openalex.org/W7052901776"],"related_works":["https://openalex.org/W1600259599","https://openalex.org/W1630865680","https://openalex.org/W2373767407","https://openalex.org/W4214692512","https://openalex.org/W3176700874","https://openalex.org/W2056031932","https://openalex.org/W3168109306","https://openalex.org/W2977677679","https://openalex.org/W2149461612","https://openalex.org/W2401089611"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,63,83,104,118],"novel":[4],"mask":[5,25,59,128,144,177,200,214,245],"estimation":[6,26,37,60,129,145,178,201,215,246],"method":[7,27,61,107,130,179,202],"for":[8,69,117,135,216,231],"missing-feature":[9,217],"reconstruction":[10],"to":[11,35,44,141,197,243],"improve":[12],"speech":[13,55,76,92,102,186],"recognition":[14,148,187],"performance":[15,149,171,188],"in":[16,113,189,227],"various":[17,158,190],"types":[18,159,191,234],"of":[19,38,49,73,86,90,160,192,235],"background":[20,50,161,193],"noise":[21,40,51,162,194,236],"conditions.":[22],"A":[23],"conventional":[24,143,199,244],"based":[28,205],"on":[29,206],"spectral":[30,77,207],"subtraction":[31],"degrades":[32],"performance,":[33],"due":[34],"incorrect":[36],"the":[39,47,53,71,74,87,91,95,100,126,136,142,153,165,175,198,211],"signal":[41],"which":[42,79,110,203],"fails":[43],"accurately":[45],"represent":[46],"variations":[48],"during":[52],"incoming":[54],"utterance.":[56],"The":[57,147,170],"proposed":[58,112,127,176,212],"utilizes":[62],"Posterior-based":[64],"Representative":[65],"Mean":[66],"(PRM)":[67],"estimate":[68],"determining":[70],"reliability":[72],"input":[75],"components,":[78],"is":[80,108,150,180,204],"obtained":[81],"as":[82],"weighted":[84],"sum":[85],"mean":[88],"parameters":[89],"model":[93,105],"using":[94,152],"posterior":[96],"probability.":[97],"To":[98],"obtain":[99,220],"noise-corrupted":[101],"model,":[103],"combination":[106],"employed,":[109],"was":[111],"our":[114],"previous":[115],"study":[116],"feature":[119],"compensation":[120],"method.":[121,146],"Experimental":[122],"results":[123],"demonstrate":[124],"that":[125,174],"provides":[131],"more":[132,182],"separable":[133],"distributions":[134],"reliable/unreliable":[137],"component":[138],"classifier":[139],"compared":[140,196,242],"evaluated":[151],"Aurora":[154],"2.0":[155],"framework":[156],"over":[157],"conditions":[163,237],"and":[164,222,238],"CU-Move":[166,239],"real-life":[167],"in-vehicle":[168],"corpus.":[169],"evaluation":[172],"shows":[173],"considerably":[181],"effective":[183],"at":[184],"increasing":[185],"conditions,":[195],"subtraction.":[208],"By":[209],"employing":[210],"PRM-based":[213],"reconstruction,":[218],"we":[219],"+23.41%":[221],"+9.45%":[223],"average":[224],"relative":[225],"improvements":[226],"word":[228],"error":[229],"rate":[230],"all":[232],"four":[233],"corpus,":[240],"respectively,":[241],"methods.":[247]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}