{"id":"https://openalex.org/W1563194370","doi":"https://doi.org/10.21437/interspeech.2008-285","title":"Adaptive beamforming and soft missing data decoding for robust speech recognition in reverberant environments","display_name":"Adaptive beamforming and soft missing data decoding for robust speech recognition in reverberant environments","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W1563194370","doi":"https://doi.org/10.21437/interspeech.2008-285","mag":"1563194370"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-285","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/A5029037494","display_name":"Marco K\u00fchne","orcid":null},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Marco K\u00fchne","raw_affiliation_strings":["University of Western  Australia"],"affiliations":[{"raw_affiliation_string":"University of Western  Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017213156","display_name":"Roberto Togneri","orcid":"https://orcid.org/0000-0002-3778-4633"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Roberto Togneri","raw_affiliation_strings":["University of Western  Australia"],"affiliations":[{"raw_affiliation_string":"University of Western  Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023874572","display_name":"Sven Nordholm","orcid":"https://orcid.org/0000-0001-8942-5328"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sven Nordholm","raw_affiliation_strings":["University of Western Australia, Perth, Australia"],"affiliations":[{"raw_affiliation_string":"University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029037494"],"corresponding_institution_ids":["https://openalex.org/I177877127"],"apc_list":null,"apc_paid":null,"fwci":1.5191,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81695556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"976","last_page":"979"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.795945405960083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7589287161827087},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.5799529552459717},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.5597803592681885},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.5341331958770752},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5275549292564392},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5270790457725525},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5241056680679321},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5141556262969971},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.42446720600128174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3614906668663025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33742547035217285},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15757259726524353},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08358713984489441}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795945405960083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7589287161827087},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.5799529552459717},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.5597803592681885},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.5341331958770752},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5275549292564392},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5270790457725525},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5241056680679321},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5141556262969971},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.42446720600128174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3614906668663025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33742547035217285},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15757259726524353},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08358713984489441},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2008-285","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-285","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:espace.curtin.edu.au:20.500.11937/40236","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11937/40236","pdf_url":null,"source":{"id":"https://openalex.org/S4306401790","display_name":"eSpace (Curtin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205640436","host_organization_name":"Curtin University","host_organization_lineage":["https://openalex.org/I205640436"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1485014097","https://openalex.org/W1533874954","https://openalex.org/W2001372085","https://openalex.org/W2034040413","https://openalex.org/W2096554907","https://openalex.org/W2110460752","https://openalex.org/W2112773389","https://openalex.org/W2134162816","https://openalex.org/W2340117379","https://openalex.org/W3157306318"],"related_works":["https://openalex.org/W2169567031","https://openalex.org/W2001172292","https://openalex.org/W2732511158","https://openalex.org/W1982169876","https://openalex.org/W4389082013","https://openalex.org/W2324276190","https://openalex.org/W1982764159","https://openalex.org/W2348931051","https://openalex.org/W2168445433","https://openalex.org/W3133250934"],"abstract_inverted_index":{"Abstract":[0],"This":[1,322],"paper":[2,219,397],"presents":[3],"a":[4,74,248,263,285,289,364,383,431],"novel":[5,46,365],"approach":[6,223,266],"to":[7,37,69,101,109,192,204,211,232,332,356,390],"combine":[8],"microphonearray":[9],"processing":[10],"and":[11,288,329,350,372,417],"robust":[12],"speech":[13,84,98,154,173,213,387],"recognition":[14,99],"for":[15,96,151],"reverberantmulti-speaker":[16],"environments.":[17],"Spatial":[18],"cues":[19,342],"are":[20,34,175,185,353],"extracted":[21],"from":[22],"amicrophone":[23],"array":[24,72],"andautomaticallyclusteredtoestimate":[25],"local-ization":[26],"masks":[27,150,328,349],"in":[28,42,104,113,122,136,144,183,230,279,300,339,408,437],"the":[29,51,54,63,66,141,164,172,188,205,226,233,252,276,280,293,302,312,318,324,334,340,348,391,404,413,418,425],"time-frequency":[30],"domain.":[31],"The":[32,239,282,375,435],"localizationmasks":[33],"then":[35,354],"used":[36],"blindly":[38,357],"design":[39,358],"adaptive":[40,89,360],"\ufb01lters":[41,199],"order":[43],"toenhancethesourcesignalspriortomissingdataspeechrecogni-tion.":[44],"A":[45,93],"evidence":[47,256,366,419],"model":[48,367],"better":[49],"exploiting":[50],"informationprovided":[52],"by":[53,224,346],"source":[55,260,286,351,380,405],"separation":[56,77,244,261,406],"stage":[57,245,262,407],"is":[58,107,267,315,398],"proposed.":[59],"Recogni-tion":[60],"experiments":[61],"demonstrate":[62],"effectiveness":[64],"of":[65,163,242,255,271,275,336,395],"schemewhen":[67],"compared":[68],"traditional":[70],"microphone":[71,86],"enhancementand":[73],"related":[75,432],"binaural":[76,147,433],"model.":[78,434],"Index":[79],"Terms":[80],":":[81],"missing":[82,152,249,414],"data":[83,153,179,250,415],"recognition,":[85],"ar-ray":[87],"processing,":[88],"beamforming":[90],"1.":[91],"Introduction":[92],"key":[94],"requirement":[95],"automatic":[97],"(ASR)technology":[100],"be":[102],"employed":[103,182],"everyday":[105],"situations":[106],"robust-ness":[108],"multiple":[110,134,359],"competing":[111],"speakers":[112,135],"reverberant":[114,195,344,392],"enclosures.While":[115],"today\u2019s":[116],"ASR":[117],"systems":[118],"still":[119],"fall":[120],"short":[121],"comparison":[123],"withhuman":[124],"listeners":[125],"some":[126],"promising":[127],"success":[128],"has":[129],"been":[130],"achieved":[131],"indealing":[132],"with":[133,247,430,440],"anechoic":[137,178],"conditions.":[138],"For":[139],"ex-ample,":[140],"work":[142],"reported":[143],"[1]":[145],"utilizes":[146],"localizationcuessuchasinterauraltimeandintensitydifferencestoestimatetime-frequency":[148],"(TF)":[149],"recognition(MD-ASR).However,inreverberantenclosuresthelocalizationcues":[155],"become":[156],"increasingly":[157],"unreliable":[158],"making":[159],"an":[160,208,221,441],"accurate":[161],"esti-mation":[162],"TF":[165,290,295],"mask":[166,291],"considerably":[167],"more":[168,409],"dif\ufb01cult.":[169],"Further-more":[170],"when":[171],"models":[174,203,257],"trained":[176],"on":[177],"thespectral":[180],"features":[181],"MD-ASR":[184],"adversely":[186],"affectedby":[187],"room":[189,206],"re\ufb02ections.Previous":[190],"attempts":[191],"handle":[193],"multisource":[194],"en-vironments":[196],"include":[197],"dereverberation":[198],"[2],":[200],"adaptation":[201],"ofspeech":[202],"[3],":[207],"inhibition":[209],"mechanism":[210],"em-phasizesoundonsets[4]andfeatureenhancementusinganane-choic":[212],"prior":[214],"based":[215],"reconstruction":[216],"technique":[217],"[5].This":[218],"proposes":[220],"alternative":[222],"extend-ing":[225],"two-channel":[227],"system":[228,240,376],"developed":[229],"[6]":[231,301],"multi-microphone":[234],"case":[235],"(see":[236],"Figure":[237],"1a).":[238],"consists":[241],"asource":[243],"coupled":[246],"decoderthrough":[251],"probabilistic":[253],"concept":[254],"[7].":[258],"Forthe":[259],"fuzzy":[264],"clustering":[265,283],"em-ployed":[268],"using":[269],"direction":[270],"arrival":[272],"(DOA)":[273],"values":[274],"two":[277],"outersensors":[278],"array.":[281],"produces":[284],"DOAestimate":[287],"marking":[292],"dominant":[294],"points":[296],"foreach":[297],"source.":[298],"While":[299],"correlation":[303],"between":[304],"adjacent":[305],"TFpoints":[306],"wasonly":[307],"utilized":[308],"duringmask":[309],"post-processing":[310],"inthispa-per":[311],"neighborhood":[313],"information":[314,371],"integrated":[316],"during":[317],"clus-tering":[319],"process":[320],"itself.":[321],"biases":[323],"solution":[325],"towards":[326],"homoge-nous":[327],"helps":[330],"greatly":[331],"reduce":[333],"effect":[335],"noise":[337],"visi-ble":[338],"localization":[341,381],"under":[343],"conditions.Motivated":[345],"[8]":[347],"DOAs":[352],"uti-lized":[355],"beamformers":[361],"capableofenhancingthespeechsourcespriortorecognition.":[362],"Thisworkproposes":[363],"incorporating":[368],"both":[369],"localiza-tion":[370],"feature":[373],"uncertainty.":[374],"operatesinanunsupervised":[377],"manneranddependsneither":[378],"ontrainingdatafor":[379],"nor":[382],"priori":[384],"learned":[385],"echoic":[386],"mod-els":[388],"adapted":[389],"environment.The":[393],"remainder":[394],"this":[396],"as":[399],"follows:":[400],"Section":[401,411,422,438],"2":[402],"de-scribes":[403],"detail.":[410],"3discusses":[412],"recognizer":[416],"modelparameter":[420],"estimation.":[421],"4":[423],"reports":[424],"evaluation":[426],"resultsand":[427],"compares":[428],"these":[429],"papercloses":[436],"5":[439],"outlook":[442],"into":[443],"future":[444],"work.":[445]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}