{"id":"https://openalex.org/W135396087","doi":"https://doi.org/10.21437/interspeech.2004-653","title":"A wizard of oz framework for collecting spoken human-computer dialogs","display_name":"A wizard of oz framework for collecting spoken human-computer dialogs","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W135396087","doi":"https://doi.org/10.21437/interspeech.2004-653","mag":"135396087"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-653","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-653","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/A5077471718","display_name":"Rohit Mishra","orcid":"https://orcid.org/0000-0002-8461-4223"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Mishra","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006981397","display_name":"Sandra Upson","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandra Upson","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101821908","display_name":"Joyce Chen","orcid":"https://orcid.org/0009-0006-5507-2265"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joyce Chen","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103540001","display_name":"Fuliang Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fuliang Weng","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039274566","display_name":"Stanley Peters","orcid":"https://orcid.org/0000-0003-4920-3506"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stanley Peters","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023819089","display_name":"Lawrence Cavedon","orcid":"https://orcid.org/0000-0001-7464-857X"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lawrence Cavedon","raw_affiliation_strings":["Robert Bosch-GmbH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch-GmbH","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008629","display_name":"John Niekrasz","orcid":null},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"John Niekrasz","raw_affiliation_strings":["Robert Bosch-GmbH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch-GmbH","institution_ids":["https://openalex.org/I889804353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102840416","display_name":"Hua Cheng","orcid":"https://orcid.org/0000-0003-1109-7832"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hua Cheng","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051405063","display_name":"Harry Bratt","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harry Bratt","raw_affiliation_strings":["SRI, International;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8821,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.70169155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2269","last_page":"2272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T10470","display_name":"Usability and User Interface Design","score":0.9760000109672546,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/dialog-box","display_name":"Dialog box","score":0.8159090280532837},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7970438599586487},{"id":"https://openalex.org/keywords/wizard","display_name":"Wizard","score":0.7632296681404114},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6626576781272888},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6196117401123047},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5240231156349182},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.5155072212219238},{"id":"https://openalex.org/keywords/wizard-of-oz","display_name":"Wizard of oz","score":0.4793199300765991},{"id":"https://openalex.org/keywords/cognitive-load","display_name":"Cognitive load","score":0.4202679991722107},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.3439306914806366},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.20422610640525818},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11360371112823486}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8159090280532837},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7970438599586487},{"id":"https://openalex.org/C2776784076","wikidata":"https://www.wikidata.org/wiki/Q580334","display_name":"Wizard","level":2,"score":0.7632296681404114},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6626576781272888},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6196117401123047},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5240231156349182},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5155072212219238},{"id":"https://openalex.org/C2987423310","wikidata":"https://www.wikidata.org/wiki/Q18159725","display_name":"Wizard of oz","level":2,"score":0.4793199300765991},{"id":"https://openalex.org/C61641136","wikidata":"https://www.wikidata.org/wiki/Q1107019","display_name":"Cognitive load","level":3,"score":0.4202679991722107},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3439306914806366},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20422610640525818},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11360371112823486},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-653","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-653","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W157172745","https://openalex.org/W1571653308","https://openalex.org/W1585333835","https://openalex.org/W1721378200","https://openalex.org/W2056561350","https://openalex.org/W2101308260"],"related_works":["https://openalex.org/W4246078203","https://openalex.org/W659328528","https://openalex.org/W48079147","https://openalex.org/W1550648368","https://openalex.org/W2394821827","https://openalex.org/W2127135847","https://openalex.org/W4402443486","https://openalex.org/W603474643","https://openalex.org/W2152818631","https://openalex.org/W2563921006"],"abstract_inverted_index":{"Abstract":[0],"This":[1,65],"paper":[2,66],"describes":[3],"a":[4,30,75,181,245,248,262,291,319,325,328,410,435,442,549,558,578,642,673],"data":[5,42,73,233,394,446,503,516,606],"collection":[6,234,395],"process":[7],"aimed":[8],"atgathering":[9],"human-computer":[10,83],"dialogs":[11,462],"in":[12,74,82,168,225,454,488,497,577,613],"high-stress":[13],"or":[14,98,127,203],"\u201cbusy\u201ddo-mains":[15],"where":[16,89],"the":[17,41,48,90,102,110,117,133,161,176,214,238,270,277,280,283,288,316,357,360,371,380,386,397,402,421,455,472,515,523,528,541,623,661],"user":[18,118,162,257,422],"is":[19,38,251,261,351,517,557],"concentrating":[20],"on":[21,236,276,522,601],"tasks":[22,373,602],"other":[23,100],"than":[24],"theconversation,":[25],"for":[26,36,61,70,296,337,342,412,506,583],"example,":[27],"when":[28,599],"driving":[29,77,95,531],"car.":[31],"Designing":[32],"spo-ken":[33],"dialog":[34,49,177,294,349,414,417,643],"interfaces":[35,84],"suchdomains":[37],"extremely":[39],"challengingand":[40],"collected":[43],"will":[44,107,218],"help":[45,108,641,668,678],"us":[46,375],"improve":[47],"systemin-terfaceand":[50],"performance,understandhowhumansperformthesetasks":[51],"with":[52,538],"respect":[53,539],"to":[54,216,352,362,376,423,450,460,467,470,482,540,548,561,573,589,672,677],"stressful":[55],"situations,":[56],"and":[57,131,136,172,198,206,209,247,273,282,307,327,335,359,378,405,466,551,592,627,649,652],"obtain":[58],"speech":[59,72,171,183,241,581],"ut-terances":[60],"extracting":[62,584],"prosodic":[63,609],"features.":[64],"describesthe":[67],"experimental":[68],"design":[69],"collecting":[71,237,368],"simu-lated":[76],"environment.":[78],"1.":[79],"Background":[80],"Research":[81],"has":[85,396,408,504],"been":[86,153,409],"carried":[87,635],"outinapplications":[88],"useris":[91],"focusedon":[92],"taskssuch":[93],"as":[94,252,255,300,481],"acar":[96],"[4]":[97],"operating":[99,297],"machinery,with":[101],"goal":[103,260,346],"of":[104,140,148,175,194,240,312,347,389,434,445,527,568,625],"designinginterfaces":[105],"that":[106,213,221,250,256,447,509,634],"reduce":[109],"user\u2019s":[111,271,278],"overall":[112],"cognitive":[113],"load.In":[114],"such":[115,149,299,383],"applications,":[116],"normally":[119],"controls":[120],"several":[121],"devicessimultaneously.":[122],"Existing":[123],"applications":[124],"maintain":[125],"little":[126],"no":[128],"dia-log":[129],"context,":[130,178],"require":[132],"userto":[134],"learn":[135],"remember":[137],"compli-cated":[138],"sets":[139],"device-speci\ufb01c":[141],"commands.":[142],"To":[143],"overcome":[144],"some":[145],"ofthe":[146,544],"shortcomings":[147],"systems,":[150],"researchers":[151],"have":[152],"inves-tigating":[154],"designing":[155],"spokeninterface":[156],"systems":[157,508],"which":[158,657],"can":[159,437,640,666],"conversewith":[160],"more":[163,166],"naturally,":[164],"allowing":[165],"\ufb02exibility":[167],"th":[169],"euser\u2019s":[170],"keeping":[173],"track":[174],"similarto":[179],"how":[180,492],"human":[182,246,501],"partner":[184],"would":[185,258,486,571],"[6,":[186],"7].":[187],"However,":[188],"human-humanspeechin":[189],"suchscenariosis":[190],"highly":[191],"context-and":[192],"situation-dependent,full":[193],"dis\ufb02uencies(e.g.,":[195],"false":[196],"starts":[197],"paus":[199],"es)andsentence":[200],"fragments":[201],"(abandoned":[202],"repaired":[204],"utterances),":[205],"ishighly":[207],"interactive":[208],"collaborative.":[210],"We":[211,286,331],"believe":[212],"easiestinterfaces":[215],"use":[217,287,332,468,572],"be":[219,363,439],"those":[220],"mimic":[222,265],"human-human":[223,266,369],"inter-action":[224],"some,":[226],"though":[227],"perhaps":[228],"not":[229],"all,":[230],"respects.":[231],"Therefore,our":[232],"focuses":[235],"kind":[239],"thatwould":[242],"occur":[243],"between":[244,356],"system":[249,263,350,361,381,391,403,418,436,644],"\ufb02exibleand":[253],"capable":[254],"desire.Our":[259],"should":[264,419],"interac-tions":[267],"by":[268],"understanding":[269,321,474],"requests":[272],"producing":[274],"re-sponsesbased":[275],"knowledge,":[279],"conversationalcon-text,":[281],"external":[284,552],"situation.":[285],"car-driving":[289],"domainas":[290],"testbed":[292],"ofsucha":[293],"interface":[295,404],"in-carequip-ment,":[298],"obtaining":[301],"navigation":[302,495,502,575],"information":[303,308,576,610,632,670],"(e.g.,":[304,546,615,619],"turn-by-turn":[305],"instructions)":[306],"about":[309],"local":[310],"points":[311],"interest.Figure":[313],"1":[314],"illustrates":[315],"systemcomponents,which":[317],"include":[318],"lan-guage":[320],"component,a":[322],"response":[323],"generator,":[324],"dialogmanager":[326],"prosody":[329,585],"classi\ufb01er.":[330],"off-the-shelf":[333],"tech-nologies":[334],"tools":[336],"speechrecognition,":[338],"speechsynthesis,andknowledge":[339],"management.1.1.":[340],"Purposes":[341],"Data":[343],"CollectionThe":[344],"ultimate":[345],"our":[348,390],"enable":[353],"natural":[354,674],"in-teractions":[355],"driver":[358,647],"like":[364],"thosebetween":[365],"humans.":[366],"Therefore":[367],"dialogsfor":[370],"above":[372],"helps":[374],"develop":[377],"tune":[379],"tosimulate":[382],"interactions.":[384],"As":[385],"\ufb01rst":[387],"step":[388],"de":[392],"-velopment,":[393],"following":[398],"speci\ufb01c":[399],"purpo":[400],"ses.Improve":[401],"performance:":[406],"Languagecoverage":[407],"bottleneck":[411],"existing":[413],"systems.":[415],"Arobust":[416],"allow":[420],"speak":[424],"freely":[425],"andbe":[426],"ableto":[427],"understandthe":[428],"user\u2019sintention":[429],"expressedthroughvar-ious":[430],"utterances.":[431],"The":[432,476],"robustness":[433],"only":[438],"en-hanced":[440],"using":[441],"large":[443],"amount":[444],"are":[448,587],"expected":[449],"covermost":[451],"language":[452,473,675],"phenomena":[453],"target":[456],"application.":[457],"Thereforewe":[458],"aim":[459],"collect":[461,562],"from":[463],"many":[464],"subjects":[465],"thesedata":[469],"train":[471],"component.":[475],"datawill":[477],"also":[478,667],"provide":[479],"evidence":[480],"what":[483,566],"features":[484,630],"users":[485],"de-sire":[487],"an":[489],"in-car":[490],"conversationalsystem.Understand":[491],"humans":[493,570],"give":[494,535],"instructions":[496],"adriving":[498],"situation:":[499],"Although":[500],"beencollected":[505],"developing":[507],"automatically":[510],"generatenavigation":[511],"instructions,":[512],"e.g.":[513],"[1],":[514],"often":[518],"written":[519],"de-scriptions":[520],"based":[521],"subject\u2019s":[524],"mental":[525],"recap":[526],"route.":[529],"Ina":[530],"environment,humans":[532],"might":[533],"chooseto":[534],"navigationinformation":[536],"differently":[537],"current":[542],"position":[543],"vehicle":[545],"close":[547],"turn)":[550],"situations":[553],"(e.g.,emergency":[554],"stop).":[555],"There":[556],"need,":[559],"therefore,":[560],"new":[563],"datato":[564],"discover":[565],"kinds":[567],"strategies":[569],"con-vey":[574],"real-time":[579],"setting.Obtain":[580],"utterances":[582],"features:Drivers":[586],"likely":[588],"produce":[590],"dis\ufb02uent":[591],"distracted":[593],"speec":[594],"hwith":[595],"potentially":[596],"complex":[597],"syntax":[598],"focusing":[600],"otherthan":[603],"talking.":[604],"Such":[605],"contain":[607],"rich":[608],"thatcaptures":[611],"variations":[612],"timing":[614],"lengthened":[616],"sounds,":[617],"pauses),intonation":[618],"pitch":[620],"rise/fall":[621],"at":[622],"end":[624],"utterance),":[626],"loud-ness.":[628],"These":[629],"convey":[631],"beyond":[633],"bythe":[636],"words":[637],"themselves.":[638],"They":[639,665],"detectutterance":[645],"boundaries,":[646],"intention":[648],"stress":[650],"level,":[651],"sub-sequently":[653],"generate":[654],"appropriate":[655],"responses":[656],"take":[658],"into":[659],"ac-count":[660],"driver\u2019s":[662],"emotional":[663],"state.":[664],"augmentthe":[669],"available":[671],"parser,":[676]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}