{"id":"https://openalex.org/W88744088","doi":null,"title":"Multilingual Spoken Term Detection: Finding and Testing New Pronunciations","display_name":"Multilingual Spoken Term Detection: Finding and Testing New Pronunciations","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W88744088","mag":"88744088"},"language":"en","primary_location":{"id":"mag:88744088","doi":null,"is_oa":false,"landing_page_url":"http://www.clsp.jhu.edu/vfsrv/workshops/ws08/documents/report.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","indexed_in":[],"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/A5063612469","display_name":"Richard Sproat","orcid":"https://orcid.org/0000-0002-9040-5196","observed_orcids":["https://orcid.org/0000-0002-9040-5196"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard Sproat","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9040-5196","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"J. Wesley Baker","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Wesley Baker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069254823","display_name":"Martin Jansche","orcid":"https://orcid.org/0000-0003-0484-4879","observed_orcids":["https://orcid.org/0000-0003-0484-4879"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Jansche","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0484-4879","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":"https://orcid.org/0000-0002-8049-2345","observed_orcids":["https://orcid.org/0000-0002-8049-2345"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014137885","display_name":"Michael Riley","orcid":"https://orcid.org/0009-0002-9449-025X","observed_orcids":["https://orcid.org/0009-0002-9449-025X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Riley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088302697","display_name":"Abhinav Sethy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhinav Sethy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065795662","display_name":"Patrick J. Wolfe","orcid":"https://orcid.org/0000-0003-3669-2777","observed_orcids":["https://orcid.org/0000-0003-3669-2777"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick J. Wolfe","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3669-2777","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev P. Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897","observed_orcids":["https://orcid.org/0000-0001-5976-0897"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5976-0897","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016623654","display_name":"Arnab Kumar Ghoshal","orcid":"https://orcid.org/0000-0003-1272-2599","observed_orcids":["https://orcid.org/0000-0003-1272-2599"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arnab Ghoshal","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1272-2599","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043447750","display_name":"Kristy Hollingshead","orcid":"https://orcid.org/0000-0002-4900-0517","observed_orcids":["https://orcid.org/0000-0002-4900-0517"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristy Hollingshead","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4900-0517","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108227299","display_name":"Chris White","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris White","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043567153","display_name":"Ting Qian","orcid":"https://orcid.org/0000-0001-6113-0341","observed_orcids":["https://orcid.org/0000-0001-6113-0341","https://orcid.org/0000-0001-5872-7024"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Qian","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6113-0341","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793","observed_orcids":["https://orcid.org/0000-0002-2978-2793"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2978-2793","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053473331","display_name":"Morgan Ulinski","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morgan Ulinski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1147,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88508554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6654999852180481,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.6654999852180481,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.29350000619888306,"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/T12031","display_name":"Speech and dialogue systems","score":0.006599999964237213,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.7799999713897705},{"id":"https://openalex.org/keywords/pronunciation-variation","display_name":"pronunciation variation","score":0.3580000102519989},{"id":"https://openalex.org/keywords/cross-lingual-search","display_name":"cross-lingual search","score":0.38999998569488525},{"id":"https://openalex.org/keywords/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.42500001192092896},{"id":"https://openalex.org/keywords/multilingual-text-to-speech","display_name":"multilingual text-to-speech","score":0.7540000081062317},{"id":"https://openalex.org/keywords/multilingual-speech-synthesis","display_name":"multilingual speech synthesis","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7999365329742432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.620837390422821},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5922535061836243},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.5286802649497986},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5008549690246582},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.49685338139533997},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4478873312473297},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37241894006729126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37116068601608276},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.12298688292503357},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:88744088","doi":null,"is_oa":false,"landing_page_url":"http://www.clsp.jhu.edu/vfsrv/workshops/ws08/documents/report.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W49437105","https://openalex.org/W74970197","https://openalex.org/W114193738","https://openalex.org/W120415783","https://openalex.org/W128271544","https://openalex.org/W183136171","https://openalex.org/W1506201763","https://openalex.org/W1526729636","https://openalex.org/W1529355025","https://openalex.org/W1540719499","https://openalex.org/W1555835807","https://openalex.org/W1563762850","https://openalex.org/W1646278814","https://openalex.org/W1659709314","https://openalex.org/W1779680350","https://openalex.org/W1831974383","https://openalex.org/W1860547055","https://openalex.org/W1878590289","https://openalex.org/W1904457459","https://openalex.org/W1934041838","https://openalex.org/W1963760715","https://openalex.org/W1963993153","https://openalex.org/W1970195330","https://openalex.org/W1985833281","https://openalex.org/W2004329216","https://openalex.org/W2015688877","https://openalex.org/W2030019187","https://openalex.org/W2055543848","https://openalex.org/W2063401344","https://openalex.org/W2066308426","https://openalex.org/W2074932712","https://openalex.org/W2075241709","https://openalex.org/W2084988910","https://openalex.org/W2090362702","https://openalex.org/W2096648470","https://openalex.org/W2102443632","https://openalex.org/W2104770448","https://openalex.org/W2105852393","https://openalex.org/W2111338354","https://openalex.org/W2112063135","https://openalex.org/W2115513413","https://openalex.org/W2117339024","https://openalex.org/W2117408078","https://openalex.org/W2119013622","https://openalex.org/W2120234416","https://openalex.org/W2121155963","https://openalex.org/W2126315862","https://openalex.org/W2127000031","https://openalex.org/W2127095586","https://openalex.org/W2127361019","https://openalex.org/W2127611282","https://openalex.org/W2128574729","https://openalex.org/W2129742890","https://openalex.org/W2138477841","https://openalex.org/W2139812240","https://openalex.org/W2144087290","https://openalex.org/W2149427046","https://openalex.org/W2151521349","https://openalex.org/W2151858239","https://openalex.org/W2152731658","https://openalex.org/W2155427043","https://openalex.org/W2156431836","https://openalex.org/W2161935199","https://openalex.org/W2163069610","https://openalex.org/W2166202273","https://openalex.org/W2168119002","https://openalex.org/W2183390198","https://openalex.org/W2540805764","https://openalex.org/W2913739034","https://openalex.org/W2949089825"],"related_works":["https://openalex.org/W2400208341","https://openalex.org/W7098406383","https://openalex.org/W2040070072","https://openalex.org/W7095638352","https://openalex.org/W6996681534","https://openalex.org/W6912870736","https://openalex.org/W2155330785","https://openalex.org/W4408519969","https://openalex.org/W2748394715","https://openalex.org/W7100066443"],"abstract_inverted_index":{"When":[0],"you":[1,21,38],"listen":[2],"to":[3,66,91,94,98,121,124,128,130,191,217,243,252,268,289,338,401,426,436,440,458,465,510,534,546],"the":[4,138,176,189,246,249,254,259,265,270,287,349,381,385,389,408,422,467,481,491,536],"evening":[5],"news,":[6],"or":[7,12,24,48,87,100,117,132,296],"read":[8],"a":[9,17,26,30,33,81,84,96,108,114,208,232,444,452,471,476],"newspaper,":[10],"book":[11],"web":[13,190,318,366,423],"site,":[14],"there":[15],"is":[16,231,280,303],"good":[18],"chance":[19],"that":[20,37,181,310,486],"will":[22],"hear":[23],"see":[25],"term":[27,35,165,168,412,431,497],"\u2014":[28,36],"perhaps":[29,32],"name,":[31],"technical":[34],"have":[39],"never":[40],"seen":[41],"before.":[42],"Such":[43],"words":[44],"are":[45,51,62,70,182,311,325,424,434,499,531],"often":[46,52],"novel":[47,453],"rare":[49],"and":[50,76,167,202,262,384,392,464,561,574],"names":[53,576],"(of":[54],"people,":[55],"places,":[56],"organizations.":[57],".":[58,59],").":[60],"They":[61],"hard":[63],"for":[64,73,236,342,348,429,442,503,549,569],"humans":[65],"process,":[67],"but":[68],"they":[69],"even":[71],"harder":[72],"automatic":[74,504,517],"speech":[75,85,399,445],"language":[77],"processing":[78],"systems.":[79],"For":[80,103,136,170,553],"single":[82],"language,":[83],"recognition":[86],"text-to-speech":[88],"system":[89,213],"needs":[90,120],"know":[92,122],"how":[93,123],"pronounce":[95],"word":[97,127,260],"recognize":[99],"say":[101],"it.":[102],"two":[104],"languages,":[105],"in":[106,142,154,185,226,245,443,447,462,500,539,579],"particular":[107],"pair":[109],"with":[110,321,480],"different":[111,417],"writing":[112],"systems,":[113],"search":[115,441],"engine":[116],"document":[118],"summarizer":[119],"transcribe":[125],"one":[126,282,469],"another":[129,448],"retrieve":[131],"distill":[133],"across":[134,572,577],"languages.":[135],"example,":[137],"soccer":[139],"player":[140],"written":[141],"English":[143],"text":[144,562],"as":[145,150,199,215,358,371,524,526,565,567,583],"Maciej":[146],"Zurawski":[147],"would":[148],"appear":[149],"\ub9c8\uce58\uc5d0\uc774\uc8fc\ub77c\ube0c\uc2a4\ud0a4":[151],"(ma-chi-e-i":[152],"ju-ra-beu-seu-ki)":[153],"Korean":[155],"In":[156],"this":[157,512,516],"project":[158],"we":[159,172,241,555],"attack":[160],"both":[161,380],"problems":[162],"\u2013":[163,228,559,564],"unusual":[164],"pronunciation":[166,271,391,404,538],"transcription.":[169],"pronunciation,":[171,255],"make":[173,256,377],"use":[174,207,257,378,398,451,556],"of":[175,179,248,258,283,353,379,410,473,506,541],"huge":[177],"numbers":[178],"pronunciations":[180,428,461,489,548],"now":[183],"available":[184,557],"various":[186],"forms":[187],"on":[188,494],"mine":[192],"pronunciations.":[193,327],"This":[194],"ranges":[195],"from":[196,330,364,421,470],"straightforward,":[197],"such":[198,214,219,370],"dictionary":[200],"sites":[201],"Wikipedia":[203,331],"entries":[204],"where":[205,286],"people":[206],"fairly":[209],"strict":[210],"phonetic":[211,355,570],"transcription":[212,433],"IPA,":[216],"difficult":[218,351],"as:":[220],"\u2022":[221],"Trio":[222],"Shares":[223],"Nobel":[224,230],"Prize":[225],"Medicine":[227],"The":[229,278],"particularly":[233],"striking":[234],"achievement":[235],"Capecchi":[237],"(pronounced":[238],"kuh-PEK\u2019-ee).":[239],"Here":[240],"need":[242],"look":[244],"vicinity":[247],"name":[250],"\u201cCapecchi\u201d":[251],"find":[253],"\u201cpronounced\u201d,":[261],"then":[263,532],"interpret":[264],"writer\u2019s":[266],"attempt":[267],"render":[269],"using":[272,415],"an":[273],"Englishbased":[274],"ad-hoc":[275,354],"\u201cphonetic\u201d":[276],"orthography.":[277,395],"problem":[279],"therefore":[281],"entity":[284,343,346,375],"extraction,":[285],"entities":[288],"extract":[290],"can":[291,332,361],"be":[292,333,362],"either":[293],"relatively":[294,297,300],"easy":[295,301],"hard.":[298],"A":[299],"case":[302,352],"Wikipedia,":[304],"which":[305],"uses":[306],"standard":[307],"IPA":[308,323],"transcriptions":[309,356],"clearly":[312],"delimited":[313],"by":[314,406],"markup.":[315],"On":[316],"general":[317],"pages,":[319],"tokens":[320,337],"Unicode":[322],"characters":[324],"potential":[326],"Data":[328],"extracted":[329],"matched":[334],"against":[335],"these":[336,416,542],"provide":[339],"training":[340],"material":[341],"extraction.":[344],"Statistical":[345],"extractors":[347,376],"more":[350],"(such":[357,582],"\u201ckuh-PEK\u2019-ee\u201d":[359],"above)":[360],"bootstrapped":[363],"unannotated":[365],"pages":[367],"containing":[368],"patterns":[369],"\u201cpronounced":[372],"as\u201d.":[373],"These":[374],"textual":[382],"environment":[383],"letter-to-sound":[386],"constraints":[387],"between":[388],"candidate":[390,460,488],"its":[393],"corresponding":[394],"We":[396,450],"also":[397],"data":[400,508],"test":[402,459,511],"possible":[403],"variants":[405],"comparing":[407],"performance":[409,493],"spoken":[411,430],"detection":[413,498],"systems":[414],"variants.":[418],"Pronunciations":[419],"mined":[420],"used":[425,435,502,533],"suggest":[427,437],"detection;":[432],"reasonable":[438],"candidates":[439,474],"stream":[446],"language.":[449],"technique":[454],"called":[455],"delayed-decision":[456],"testing":[457,478,530],"speech,":[463],"choose":[466,535],"best":[468],"set":[472],"via":[475],"sequential":[477],"procedure,":[479],"associated":[482],"null":[483,513],"hypothesis":[484],"stating":[485],"all":[487],"exhibit":[490],"same":[492],"average.":[495],"Spoken":[496],"turn":[501],"labeling":[505,518],"practice":[507],"acquired":[509],"hypothesis;":[514],"however,":[515],"procedure":[519],"inevitably":[520],"induces":[521],"false":[522,543],"alarms":[523],"well":[525,566],"correct":[527,537],"detections.":[528],"Delayed-decision":[529],"spite":[540],"alarms,":[544],"leading":[545],"improved":[547],"newly":[550],"identified":[551],"terms.":[552],"transcription,":[554],"resources":[558],"dictionaries,":[560],"corpora":[563,581],"methods":[568],"matching":[571],"scripts":[573],"tracking":[575],"time":[578],"comparable":[580],"news":[584],"sources).":[585]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2016-06-24T00:00:00"}