{"id":"https://openalex.org/W2115737782","doi":"https://doi.org/10.1109/asru.2009.5373398","title":"Mask estimation employing Posterior-based Representative Mean for missing-feature speech recognition with time-varying background noise","display_name":"Mask estimation employing Posterior-based Representative Mean for missing-feature speech recognition with time-varying background noise","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2115737782","doi":"https://doi.org/10.1109/asru.2009.5373398","mag":"2115737782"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373398","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/A5101977970","display_name":"Wooil Kim","orcid":"https://orcid.org/0000-0002-3854-2783"},"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, Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems CRSS, Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, 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, Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems CRSS, Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101977970"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":1.0574,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76505209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"198"},"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":0.9998000264167786,"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":0.9993000030517578,"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":0.6823077201843262},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6253187656402588},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6169241070747375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6150650382041931},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.553842306137085},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.553674042224884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5217012763023376},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4272359311580658},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.41662418842315674},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.327067106962204},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.07455167174339294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823077201843262},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6253187656402588},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6169241070747375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6150650382041931},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.553842306137085},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.553674042224884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217012763023376},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4272359311580658},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.41662418842315674},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.327067106962204},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.07455167174339294},{"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/asru.2009.5373398","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373398","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W79317937","https://openalex.org/W289804034","https://openalex.org/W2045036776","https://openalex.org/W2074354966","https://openalex.org/W2093985521","https://openalex.org/W2100969003","https://openalex.org/W2128653836","https://openalex.org/W2129204992","https://openalex.org/W2143855671","https://openalex.org/W2146871184","https://openalex.org/W2147287194","https://openalex.org/W2151484683","https://openalex.org/W2162213734","https://openalex.org/W2167204516","https://openalex.org/W6603280604","https://openalex.org/W6679498742"],"related_works":["https://openalex.org/W3108403339","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W4287867034","https://openalex.org/W2175872006","https://openalex.org/W4375869276"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,44,63,83,97],"novel":[4],"mask":[5,22,40,107,129,155],"estimation":[6,23,41,108,130,156],"method":[7,42,86,109],"for":[8,50,96,131,144],"missing-feature":[9,132],"reconstruction":[10],"to":[11,33,153],"improve":[12],"speech":[13,57,72,81,116,145],"recognition":[14,117],"performance":[15,118],"in":[16,92,119,142],"time-varying":[17,120],"background":[18,121,148],"noise":[19,27,122],"conditions.":[20,123],"Conventional":[21],"methods":[24],"based":[25],"on":[26],"estimates":[28],"and":[29,137,147],"spectral":[30],"subtraction":[31],"fail":[32],"reliably":[34],"estimate":[35],"the":[36,52,55,67,71,79,105,126],"mask.":[37],"The":[38],"proposed":[39,91,106,127],"utilizes":[43],"posterior-based":[45],"representative":[46],"mean":[47,68],"(PRM)":[48],"vector":[49],"determining":[51],"reliability":[53],"of":[54,66,70],"input":[56],"spectrum,":[58],"which":[59,89],"is":[60,87,110],"obtained":[61],"as":[62],"weighted":[64],"sum":[65],"parameters":[69],"model":[73,84],"with":[74],"posterior":[75],"probabilities.":[76],"To":[77],"obtain":[78,135],"noise-corrupted":[80],"model,":[82],"combination":[85],"employed,":[88],"was":[90],"our":[93],"previous":[94],"study":[95],"feature":[98],"compensation":[99],"method.":[100],"Experimental":[101],"results":[102],"demonstrate":[103],"that":[104],"considerably":[111],"more":[112],"effective":[113],"at":[114],"increasing":[115],"By":[124],"employing":[125],"PRM-based":[128],"reconstruction,":[133],"we":[134],"+36.29%":[136],"+30.45%":[138],"average":[139],"relative":[140],"improvements":[141],"WER":[143],"babble":[146],"music":[149],"conditions":[150],"respectively,":[151],"compared":[152],"conventional":[154],"methods.":[157]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}