{"id":"https://openalex.org/W2602119218","doi":"https://doi.org/10.1109/ita.2016.7888198","title":"Language coverage for mismatched crowdsourcing","display_name":"Language coverage for mismatched crowdsourcing","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2602119218","doi":"https://doi.org/10.1109/ita.2016.7888198","mag":"2602119218"},"language":"en","primary_location":{"id":"doi:10.1109/ita.2016.7888198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2016.7888198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Information Theory and Applications Workshop (ITA)","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/A5065423139","display_name":"Lav R. Varshney","orcid":"https://orcid.org/0000-0003-2798-5308"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lav R. Varshney","raw_affiliation_strings":["Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036738038","display_name":"Preethi Jyothi","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Preethi Jyothi","raw_affiliation_strings":["Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9975000023841858,"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":0.9975000023841858,"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/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/crowdsourcing","display_name":"Crowdsourcing","score":0.9637271165847778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.761233925819397},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5701340436935425},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5569507479667664},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5482289791107178},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5267153382301331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46907728910446167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45749199390411377},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.43553388118743896},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41954925656318665},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24776607751846313},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11117708683013916},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.08541369438171387}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.9637271165847778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761233925819397},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5701340436935425},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5569507479667664},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5482289791107178},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5267153382301331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46907728910446167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45749199390411377},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.43553388118743896},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41954925656318665},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24776607751846313},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11117708683013916},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.08541369438171387},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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:10.1109/ita.2016.7888198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2016.7888198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Information Theory and Applications Workshop (ITA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W97283166","https://openalex.org/W1436754857","https://openalex.org/W1488077438","https://openalex.org/W1513026569","https://openalex.org/W1526974435","https://openalex.org/W1598851216","https://openalex.org/W1956280017","https://openalex.org/W1965545650","https://openalex.org/W1970381522","https://openalex.org/W1972939083","https://openalex.org/W1973200191","https://openalex.org/W1976587578","https://openalex.org/W1980044217","https://openalex.org/W1989645203","https://openalex.org/W1995875735","https://openalex.org/W2002182716","https://openalex.org/W2010800472","https://openalex.org/W2012850743","https://openalex.org/W2018084781","https://openalex.org/W2020214791","https://openalex.org/W2044742133","https://openalex.org/W2061129250","https://openalex.org/W2076271853","https://openalex.org/W2079145130","https://openalex.org/W2091794796","https://openalex.org/W2101509422","https://openalex.org/W2117539524","https://openalex.org/W2124479173","https://openalex.org/W2125126745","https://openalex.org/W2136780942","https://openalex.org/W2144679335","https://openalex.org/W2152088468","https://openalex.org/W2159038374","https://openalex.org/W2165698076","https://openalex.org/W2168271389","https://openalex.org/W2182894058","https://openalex.org/W2212120078","https://openalex.org/W2314715977","https://openalex.org/W2321675883","https://openalex.org/W3021996482","https://openalex.org/W3100370256","https://openalex.org/W3125730766","https://openalex.org/W3148931049","https://openalex.org/W4238503320","https://openalex.org/W6628467411","https://openalex.org/W6641019819"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W2118730790"],"abstract_inverted_index":{"Developing":[0],"automatic":[1],"speech":[2,7,40],"recognition":[3],"technologies":[4],"requires":[5],"transcribed":[6],"so":[8],"as":[9,93],"to":[10,16,25,69],"learn":[11],"the":[12,30,37,48,100,105,137],"mapping":[13],"from":[14],"sound":[15],"text.":[17],"It":[18],"is":[19,36],"traditionally":[20],"assumed":[21],"that":[22,65],"transcribers":[23],"need":[24],"be":[26,67,91,144],"native":[27,115,119,132],"speakers":[28,117,121],"of":[29,39,78,102,107,140],"language":[31,133],"being":[32],"transcribed.":[33],"Mismatched":[34],"crowdsourcing":[35,60],"transcription":[38,142],"by":[41,146],"crowd":[42,129],"workers":[43,130],"who":[44],"do":[45],"not":[46],"speak":[47],"language.":[49],"Given":[50],"there":[51],"are":[52],"phonological":[53,76],"similarities":[54],"among":[55],"different":[56,79],"human":[57],"languages,":[58],"mismatched":[59],"does":[61],"provide":[62],"noisy":[63,95],"data":[64],"can":[66,90,143],"aggregated":[68],"yield":[70],"reliable":[71],"labels.":[72],"Here":[73],"we":[74,126],"discuss":[75,127],"properties":[77],"languages":[80],"in":[81],"a":[82,94,148],"coding-theoretic":[83],"framework,":[84],"and":[85,118],"how":[86,128],"nonnative":[87],"phoneme":[88],"misperception":[89],"modeled":[92],"communication":[96],"channel.":[97],"We":[98],"show":[99],"results":[101],"experiments":[103],"demonstrating":[104],"efficacy":[106],"this":[108],"information":[109],"theory":[110],"inspired":[111],"modeling":[112],"approach,":[113],"having":[114],"English":[116],"Mandarin":[120],"transcribe":[122],"Cantonese":[123],"speech.":[124],"Finally":[125],"whose":[131],"background":[134],"give":[135],"them":[136],"highest":[138],"probability":[139],"faithful":[141],"found":[145],"solving":[147],"weighted":[149],"set":[150],"cover":[151],"problem.":[152]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}