{"id":"https://openalex.org/W95078122","doi":"https://doi.org/10.21437/interspeech.2004-570","title":"Coping with disfluencies in spontaneous speech recognition","display_name":"Coping with disfluencies in spontaneous speech recognition","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W95078122","doi":"https://doi.org/10.21437/interspeech.2004-570","mag":"95078122"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"conference-paper","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/A5076839160","display_name":"Frederik Stouten","orcid":null},"institutions":[{"id":"https://openalex.org/I2801227569","display_name":"Ghent University Hospital","ror":"https://ror.org/00xmkp704","country_code":"BE","type":"healthcare","lineage":["https://openalex.org/I2801227569"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Frederik Stouten","raw_affiliation_strings":["Ghent University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University","institution_ids":["https://openalex.org/I2801227569"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109810030","display_name":"Jean\u2010Pierre Martens","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Pierre Martens","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1513","last_page":"1516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10730","display_name":"Language Development and Disorders","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9969000220298767,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7976243495941162},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.7842600345611572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6953461170196533},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6671798825263977},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6023393869400024},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5934422612190247},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5293769836425781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4846823513507843},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.4420399069786072},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4161611497402191},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2587016820907593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976243495941162},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.7842600345611572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6953461170196533},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6671798825263977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6023393869400024},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5934422612190247},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5293769836425781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846823513507843},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.4420399069786072},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4161611497402191},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2587016820907593},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-570","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:318977","is_oa":false,"landing_page_url":"https://biblio.ugent.be/publication/318977","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the International Conference on Spoken Language Processing","raw_type":"info:eu-repo/semantics/conferenceObject"}],"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/W84258004","https://openalex.org/W205128995","https://openalex.org/W1504087286","https://openalex.org/W1656790015","https://openalex.org/W2043547528","https://openalex.org/W2079577056","https://openalex.org/W2093729408","https://openalex.org/W2118379849","https://openalex.org/W2124246394","https://openalex.org/W2159515240"],"related_works":["https://openalex.org/W2105076537","https://openalex.org/W2020757772","https://openalex.org/W2072223048","https://openalex.org/W2041167939","https://openalex.org/W2950575438","https://openalex.org/W2002221802","https://openalex.org/W2250909759","https://openalex.org/W1975573722","https://openalex.org/W32588857","https://openalex.org/W1620568205"],"abstract_inverted_index":{"Abstract":[0],"Nowadays,":[1],"automatic":[2],"speech":[3,13,21,241,248,344,380,531],"recognizers":[4],"have":[5],"become":[6,448],"quite":[7],"goodin":[8],"recognizing":[9],"well":[10],"prepared":[11],"\ufb02uent":[12],"(e.g.":[14],"news":[15],"readings).However,":[16],"the":[17,65,72,80,113,150,164,179,200,212,225,251,275,287,302,305,309,312,316,326,333,338,343,379,392,410,419,424,444,450,469,508,511,514,527,539,549],"recognition":[18,451,528],"of":[19,41,67,112,170,178,227,297,304,315,363,409,412,421,429,479,489,513,529,534,552],"spontaneous":[20,32,124,247,437,530],"is":[22,52,58,231,277,307,432,474],"still":[23,210],"problem-atic.":[24],"Some":[25],"important":[26,462],"reasons":[27],"for":[28,48,88,187,233,257,267],"this":[29,239,256,517],"are":[30,206,221,261,426,460],"that":[31,76,230,329,346,427,490],"speechis":[33],"usually":[34],"less":[35],"articulated":[36],"and":[37,62,74,92,279,321,350,384,404,556,560,565],"contains":[38],"a":[39,45,110,132,168,176,193,246,258,270,397,405,430,480,486],"lot":[40],"dis\ufb02uencies.":[42],"In":[43,166,377,543],"thispaper,":[44],"new":[46],"methodology":[47],"coping":[49],"with":[50,137,195,299,418],"dis\ufb02uencies":[51,61,69,122],"presentedand":[53],"evaluated.":[54],"The":[55,118,353],"basic":[56,550],"idea":[57],"to":[59,63,71,78,98,148,192,217,254,292,325,382],"detect":[60],"deter-mine":[64],"nature":[66],"these":[68],"prior":[70],"recognition,":[73],"touse":[75],"information":[77],"control/modify":[79],"search.":[81],"At":[82],"present,":[83],"themethodology":[84],"has":[85,131,454],"been":[86,455],"elaborated":[87],"\ufb01lled":[89,126],"pauses":[90,127],"(FP)":[91],"wordrepetitions":[93],"(WR).":[94,472],"It":[95,473],"enables":[96],"us":[97],"eliminate":[99],"about":[100],"one":[101,130,141,196],"associated":[102],"normal":[103],"word":[104,180,218,470,484],"error":[105,181],"per":[106],"dis\ufb02uency":[107,463],"without":[108,537],"introducing":[109],"signi\ufb01cantaugmentation":[111],"computational":[114],"load.":[115],"1.":[116],"Introduction":[117],"most":[119],"frequently":[120],"occurring":[121,355],"in":[123,163,199,224,311,361,396,423,436,532,541],"speechare":[125],"(FPs).":[128],"If":[129],"suf\ufb01ciently":[133],"large":[134],"spontaneousspeech":[135],"corpus":[136],"FP":[138,146,159,173,197,204,310],"transcriptions":[139],"available,":[140,207],"can":[142,155,284],"create":[143],"ded-icated":[144],"acoustic":[145,171,498],"models":[147,160,174,205],"supplement":[149],"traditional":[151],"triphonemodel":[152],"set.":[153],"One":[154],"also":[156],"introduce":[157],"lexical":[158,500],"(pronuncia-tion":[161],"variants":[162],"lexicon).":[165],"[7],":[167],"combination":[169],"andlexical":[172],"yielded":[175],"reduction":[177],"rate":[182],"(WER)of":[183],"7.8":[184],"%":[185,399,407],"relative":[186],"medical":[188,273],"dictation":[189],"(with":[190,452],"respect":[191],"baselinesystem":[194],"model":[198,235],"lexicon).Even":[201],"when":[202,441],"good":[203],"FPs":[208,300,331,354,386,422],"may":[209],"con-fuse":[211],"recognizer":[213,509],"because":[214],"they":[215,340,506],"lead":[216],"sequences":[219],"(-grams)that":[220],"not":[222,266,433,495],"observed":[223],"kind":[226],"written":[228],"material":[229],"normallyused":[232],"language":[234,515],"(LM)":[236],"development.":[237],"Extending":[238],"mate-rialwithspontaneous":[240],"transcriptionswould":[242],"beanother":[243],"meansof":[244],"improving":[245,526],"recognizer.":[249],"However,":[250,319,502],"nec-essary":[252],"resources":[253],"accomplish":[255],"general":[259],"task":[260],"usuallynot":[262],"available":[263],"(and":[264],"certainly":[265],"Dutch).":[268],"For":[269],"limited":[271],"domainlike":[272],"dictation,":[274],"situation":[276],"different,":[278],"experiments":[280],"byPakhomov":[281],"[4]showed":[282],"thatthetechnique":[283],"work":[285],":":[286],"WERcouldbe":[288],"reduced":[289],"from":[290,332,457],"32.2":[291],"28.5":[293],"%.A":[294],"simple":[295],"way":[296],"dealing":[298],"at":[301,342,356,510,525],"level":[303,512],"LM":[306,313,425],"toignore":[308],"context":[314,335],"next":[317],"word.":[318,491],"Stol-cke":[320],"Shriberg":[322],"[8]":[323],"come":[324],"surprising":[327],"conclusion":[328],"discard-ing":[330],"trigram":[334],"actually":[336],"increases":[337],"perplexity.However,":[339],"looked":[341],"stretches":[345],"were":[347,387],"supplied":[348],"totherecognizer":[349],"thatweredelimitedonthebasisofacoustic":[351],"crite-ria.":[352],"sentence":[357,369,388,431,445],"boundaries":[358,446],"often":[359],"appeared":[360],"themiddle":[362],"such":[364,467],"stretches.":[365],"By":[366],"only":[367,447],"discarding":[368,393,420],"internal":[370],"FPsthe":[371],"perplexity":[372,403,411],"did":[373],"decrease,":[374],"as":[375,468],"expected.":[376],"[5]":[378],"stretchescorresponded":[381],"sentences":[383],"all":[385],"internal.":[389],"Forthis":[390],"material,":[391],"strategy":[394],"resulted":[395],"4":[398],"decrease":[400,408],"ofthe":[401],"overall":[402],"30":[406],"theword":[413],"after":[414],"an":[415,476],"FP.The":[416],"problems":[417],"thenotion":[428],"always":[434],"clear":[435],"speech,":[438,466],"andthat":[439],"even":[440],"it":[442,562],"is,":[443],"availableafter":[449],"FPs)":[453],"accomplished.Apart":[456],"FPs,":[458,505],"there":[459],"other":[461],"types":[464],"inspontaneous":[465],"repetition":[471,487],"de\ufb01nedas":[475],"event":[477],"consisting":[478],"completed":[481],"(not":[482],"interrupted)":[483],"(W)and":[485],"(R)":[488],"Clearly,":[492],"WRs":[493,536],"do":[494],"require":[496],"anynew":[497],"or":[499],"models.":[501],"just":[503],"like":[504],"maydisturb":[507],"model.In":[516],"paper":[518],"we":[519,546,557],"investigate":[520],"adaptive":[521,554],"search":[522],"methodologies":[523],"thataim":[524],"thevicinity":[533],"FPsand":[535],"affecting":[538],"performance":[540],"otherregions.":[542],"section":[544],"2":[545],"brie\ufb02y":[547],"outline":[548],"principles":[551],"thenew":[553],"approach":[555],"further":[558],"elaborate":[559],"evaluate":[561],"insections":[563],"3":[564],"4.":[566]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}