{"id":"https://openalex.org/W2144900591","doi":"https://doi.org/10.1109/tasl.2010.2041698","title":"Missing-Feature Reconstruction by Leveraging Temporal Spectral Correlation for Robust Speech Recognition in Background Noise Conditions","display_name":"Missing-Feature Reconstruction by Leveraging Temporal Spectral Correlation for Robust Speech Recognition in Background Noise Conditions","publication_year":2010,"publication_date":"2010-06-14","ids":{"openalex":"https://openalex.org/W2144900591","doi":"https://doi.org/10.1109/tasl.2010.2041698","mag":"2144900591"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2041698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041698","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/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 of 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), University of Texas at Dallas, Richardson, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center of 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), 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":"J Hansen","raw_affiliation_strings":["Center of 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), University of Texas at Dallas, Richardson, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center of 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), 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/A5101977970"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":1.6858,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85249303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"18","issue":"8","first_page":"2111","last_page":"2120"},"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":0.9994999766349792,"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/feature","display_name":"Feature (linguistics)","score":0.6790878772735596},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6463509798049927},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6121525168418884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5997909903526306},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.593814492225647},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5728849768638611},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5194482207298279},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5120499730110168},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2651558816432953},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.18839046359062195}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6790878772735596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6463509798049927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6121525168418884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5997909903526306},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.593814492225647},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5728849768638611},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5194482207298279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120499730110168},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2651558816432953},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.18839046359062195},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2041698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041698","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W44782307","https://openalex.org/W46735938","https://openalex.org/W79317937","https://openalex.org/W157345740","https://openalex.org/W289804034","https://openalex.org/W1488775899","https://openalex.org/W1543669765","https://openalex.org/W1845844605","https://openalex.org/W2010354808","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/W2115515280","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/W2137075158","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/W2158047270","https://openalex.org/W2162213734","https://openalex.org/W2163008623","https://openalex.org/W2167204516","https://openalex.org/W2167763959","https://openalex.org/W3147539069","https://openalex.org/W6603280604","https://openalex.org/W6629240969","https://openalex.org/W6679498742"],"related_works":["https://openalex.org/W2071828724","https://openalex.org/W1994694193","https://openalex.org/W2161865195","https://openalex.org/W170831052","https://openalex.org/W4247725880","https://openalex.org/W1006721676","https://openalex.org/W2100854157","https://openalex.org/W2978471304","https://openalex.org/W1771058801","https://openalex.org/W4285346358"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,34,53,60,84,151,192],"novel":[4],"missing-feature":[5,18,42,79],"reconstruction":[6,19,43,80,149],"method":[7,20,93,104,131],"to":[8,32,39,183],"improve":[9,40],"speech":[10,110,123,137,170],"recognition":[11,138],"in":[12,140,160,200],"background":[13,116,173],"noise":[14,117],"environments.":[15],"The":[16,75],"existing":[17],"utilizes":[21],"log-spectral":[22],"correlation":[23,48,91],"across":[24,49],"frequency":[25,90,186],"bands.":[26],"In":[27,52],"this":[28],"paper,":[29],"we":[30],"propose":[31],"employ":[33],"temporal":[35,47,71,97],"spectral":[36,72],"feature":[37,73],"analysis":[38],"the":[41,57,69,88,95,102,108,120,129,145,184,207],"performance":[44,139],"by":[45,66,83],"leveraging":[46],"neighboring":[50],"frames.":[51],"similar":[54],"manner":[55],"with":[56],"conventional":[58],"method,":[59,150],"Gaussian":[61],"mixture":[62],"model":[63],"is":[64,105,132,165],"obtained":[65,70,82,166],"training":[67],"over":[68,176],"set.":[74],"final":[76],"estimates":[77],"for":[78,167],"are":[81],"selective":[85],"combination":[86],"of":[87,101,115],"original":[89,185],"based":[92,148],"and":[94,119,172,179],"proposed":[96,103,130,146],"correlation-based":[98,187],"method.":[99,188],"Performance":[100],"evaluated":[106],"on":[107],"TIMIT":[109],"corpus":[111],"using":[112,204],"various":[113],"types":[114],"conditions":[118,175,203],"CU-Move":[121,208],"in-vehicle":[122,202],"corpus.":[124,209],"Experimental":[125],"results":[126],"demonstrate":[127],"that":[128],"more":[133],"effective":[134],"at":[135],"increasing":[136],"adverse":[141],"conditions.":[142],"By":[143],"employing":[144],"temporal-frequency":[147],"<formula":[152,193],"formulatype=\"inline\"":[153,194],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[154,195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex":[155,196],"Notation=\"TeX\">$+17.71\\%$</tex></formula>":[156],"average":[157],"relative":[158,198],"improvement":[159,199],"word":[161],"error":[162],"rate":[163],"(WER)":[164],"white,":[168],"car,":[169],"babble,":[171],"music":[174],"5-,":[177],"10-,":[178],"15-dB":[180],"SNR,":[181],"compared":[182],"We":[189],"also":[190],"obtain":[191],"Notation=\"TeX\">$+16.72\\%$</tex></formula>":[197],"real-life":[201],"data":[205],"from":[206]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}