{"id":"https://openalex.org/W2040070072","doi":"https://doi.org/10.1145/1571941.1571958","title":"Web derived pronunciations for spoken term detection","display_name":"Web derived pronunciations for spoken term detection","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2040070072","doi":"https://doi.org/10.1145/1571941.1571958","mag":"2040070072"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1571958","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","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/A5112207449","display_name":"Do\u011fan Can","orcid":null},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Dogan Can","raw_affiliation_strings":["Bogazici University, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Bogazici University, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210110987","display_name":"IIT@MIT","ror":"https://ror.org/01wp8zh54","country_code":"US","type":"facility","lineage":["https://openalex.org/I30771326","https://openalex.org/I4210110987"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["MIT, Cambridge, MA, USA","MIT, Cambridge MA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210110987"]},{"raw_affiliation_string":"MIT, Cambridge MA, USA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016623654","display_name":"Arnab Ghoshal","orcid":"https://orcid.org/0000-0003-1272-2599"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnab Ghoshal","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069254823","display_name":"Martin Jansche","orcid":"https://orcid.org/0000-0003-0484-4879"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Jansche","raw_affiliation_strings":["Google, Inc., NY, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., NY, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014137885","display_name":"Michael Riley","orcid":"https://orcid.org/0009-0002-9449-025X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Riley","raw_affiliation_strings":["Google, Inc., New York, NY, USA","Google Inc., New York, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Murat Saraclar","raw_affiliation_strings":["Bogazici University, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Bogazici University, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088302697","display_name":"Abhinav Sethy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Sethy","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053473331","display_name":"Morgan Ulinski","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Morgan Ulinski","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018012809","display_name":"Christopher White","orcid":"https://orcid.org/0000-0001-8634-0441"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher White","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5112207449"],"corresponding_institution_ids":["https://openalex.org/I4405392"],"apc_list":null,"apc_paid":null,"fwci":2.1809,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88917186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"83","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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":0.9829000234603882,"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/computer-science","display_name":"Computer science","score":0.8721218109130859},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6759474277496338},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5996158719062805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5929700136184692},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5334848165512085},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5181166529655457},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5053449273109436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3830190896987915},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13159430027008057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8721218109130859},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6759474277496338},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5996158719062805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5929700136184692},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5334848165512085},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5181166529655457},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5053449273109436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3830190896987915},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13159430027008057},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1571941.1571958","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571958","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W49437105","https://openalex.org/W120415783","https://openalex.org/W183136171","https://openalex.org/W210770835","https://openalex.org/W1506201763","https://openalex.org/W1529355025","https://openalex.org/W1582482241","https://openalex.org/W1779680350","https://openalex.org/W1860547055","https://openalex.org/W1934041838","https://openalex.org/W1970195330","https://openalex.org/W2004329216","https://openalex.org/W2015688877","https://openalex.org/W2074932712","https://openalex.org/W2088857750","https://openalex.org/W2104770448","https://openalex.org/W2111338354","https://openalex.org/W2127095586","https://openalex.org/W2155427043","https://openalex.org/W2156431836","https://openalex.org/W2168119002","https://openalex.org/W2540805764","https://openalex.org/W6631608000","https://openalex.org/W6638280674","https://openalex.org/W6638930181"],"related_works":["https://openalex.org/W1873761914","https://openalex.org/W2094492371","https://openalex.org/W1592893681","https://openalex.org/W1606923665","https://openalex.org/W1606406758","https://openalex.org/W1963586751","https://openalex.org/W4249836580","https://openalex.org/W2153015554","https://openalex.org/W88309612","https://openalex.org/W2460156081"],"abstract_inverted_index":{"Indexing":[0],"and":[1,16,79,112,142,155,177,246,252],"retrieval":[2,40],"of":[3,23,29,74,89,130,140,189,192,205,216,238],"speech":[4,43,57,239],"content":[5,44],"in":[6,63,137],"various":[7],"forms":[8],"such":[9],"as":[10,225,227],"broadcast":[11],"news,":[12],"customer":[13,32],"care":[14],"data":[15],"on-line":[17,35],"media":[18,36],"has":[19],"gained":[20],"a":[21,26,50,173,206,236],"lot":[22],"interest":[24],"for":[25,76,110,148,222],"wide":[27],"range":[28,237],"applications,":[30,41],"from":[31,152,181],"analytics":[33],"to":[34,49,125,169,172,196],"search.":[37],"For":[38],"most":[39],"the":[42,72,87,90,94,100,108,127,135,138,190,203],"is":[45,71],"typically":[46],"first":[47,61,122],"converted":[48],"lexical":[51],"or":[52],"phonetic":[53],"representation":[54],"using":[55,193],"automatic":[56],"recognition":[58],"(ASR).":[59],"The":[60],"step":[62],"searching":[64],"through":[65],"indexes":[66,240],"built":[67],"on":[68,106,116,134,202,242],"these":[69,194],"representations":[70,180],"generation":[73,224],"pronunciations":[75,111,151,168,195,218,228],"named":[77],"entities":[78],"foreign":[80],"language":[81],"query":[82,200],"terms.":[83],"This":[84],"paper":[85],"summarizes":[86],"results":[88,234],"work":[91],"conducted":[92],"during":[93],"2008":[95],"JHU":[96],"Summer":[97],"Workshop":[98],"by":[99,230],"Multilingual":[101],"Spoken":[102],"Term":[103],"Detection":[104],"team,":[105],"mining":[107],"web":[109],"analyzing":[113],"their":[114],"impact":[115],"spoken":[117,207],"term":[118,208],"detection.":[119],"We":[120,145,184,212],"will":[121,213],"present":[123,186],"methods":[124],"use":[126],"vast":[128],"amount":[129],"pronunciation":[131,223],"information":[132],"available":[133],"Web,":[136],"form":[139],"IPA":[141,167],"ad-hoc":[143,182],"transcriptions.":[144,183],"describe":[146],"techniques":[147,221],"extracting":[149],"candidate":[150],"Web":[153,217],"pages":[154],"associating":[156],"them":[157],"with":[158],"orthographic":[159],"words,":[160],"filtering":[161],"out":[162],"poorly":[163],"extracted":[164],"pronunciations,":[165],"normalizing":[166],"better":[170],"conform":[171],"common":[174],"transcription":[175],"standard,":[176],"generating":[178],"phonemic":[179],"then":[185],"an":[187],"analysis":[188],"effectiveness":[191],"represent":[197],"Out-Of-Vocabulary":[198],"(OOV)":[199],"terms":[201],"performance":[204],"detection":[209],"(STD)":[210],"system.":[211],"provide":[214],"comparisons":[215],"against":[219],"automated":[220],"well":[226],"generated":[229],"human":[231],"experts.":[232],"Our":[233],"cover":[235],"based":[241],"lattices,":[243],"confusion":[244],"networks":[245],"one-best":[247],"transcriptions":[248],"at":[249],"both":[250],"word":[251,253],"fragments":[254],"levels.":[255]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}