{"id":"https://openalex.org/W2154624463","doi":"https://doi.org/10.1109/slt.2010.5700870","title":"Toward better crowdsourced transcription: Transcription of a year of the Let's Go Bus Information System data","display_name":"Toward better crowdsourced transcription: Transcription of a year of the Let's Go Bus Information System data","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2154624463","doi":"https://doi.org/10.1109/slt.2010.5700870","mag":"2154624463"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2010.5700870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2010.5700870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Spoken Language Technology Workshop","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/A5075469828","display_name":"Gabriel Parent","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gabriel Parent","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077285164","display_name":"Maxine Esk\u00e9nazi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxine Eskenazi","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075469828"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":15.2351,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.9893199,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"312","last_page":"317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":1.0,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.987500011920929,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9846000075340271,"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/transcription","display_name":"Transcription (linguistics)","score":0.7378997802734375},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.6220578551292419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5597286224365234},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.44211894273757935},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.271501749753952},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2000679075717926},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.14681097865104675},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12216106057167053}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7378997802734375},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.6220578551292419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5597286224365234},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.44211894273757935},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.271501749753952},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2000679075717926},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.14681097865104675},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12216106057167053},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2010.5700870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2010.5700870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE Spoken Language Technology Workshop","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.190.7062","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.190.7062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Egparent/papers/amt-transcript.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1904457459","https://openalex.org/W1970381522","https://openalex.org/W1973200191","https://openalex.org/W1975113979","https://openalex.org/W2057919624","https://openalex.org/W2115915304","https://openalex.org/W2117092977","https://openalex.org/W2125943921","https://openalex.org/W2139453310","https://openalex.org/W2250930911","https://openalex.org/W2395974568","https://openalex.org/W6677378386","https://openalex.org/W6691265586","https://openalex.org/W6712452078"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Transcription":[0],"is":[1,93,141],"typically":[2],"a":[3,21,32,73,114],"long":[4],"and":[5,84,131],"expensive":[6],"process.":[7],"In":[8],"the":[9,36,64,87,90,110,132,143,146,156],"last":[10],"year,":[11],"crowdsourcing":[12],"through":[13],"Amazon":[14],"Mechanical":[15],"Turk":[16],"(MTurk)":[17],"has":[18],"emerged":[19],"as":[20],"way":[22],"to":[23,40,52,79,95,150],"transcribe":[24,41],"large":[25],"amounts":[26],"of":[27,38,44,112,127,134,145],"speech.":[28],"This":[29,58],"paper":[30],"presents":[31],"two-stage":[33],"approach":[34,92,121],"for":[35,63,81],"use":[37],"MTurk":[39],"one":[42,74,101],"year":[43],"Let's":[45],"Go":[46],"Bus":[47],"Information":[48],"System":[49],"data,":[50],"corresponding":[51],"156.74":[53],"hours":[54],"(257,658":[55],"short":[56],"utterances).":[57],"data":[59],"was":[60],"made":[61],"available":[62],"Spoken":[65],"Dialog":[66],"Challenge":[67],"2010.":[68],"While":[69],"others":[70],"have":[71],"used":[72],"stage":[75,120],"approach,":[76],"asking":[77],"workers":[78],"label,":[80],"example,":[82],"words":[83],"noises":[85],"in":[86,125],"same":[88],"pass,":[89],"present":[91],"closer":[94],"what":[96],"expert":[97,153],"transcribers":[98],"do,":[99],"dividing":[100],"complicated":[102,107],"task":[103],"into":[104],"several":[105],"less":[106],"ones":[108],"with":[109,129],"goal":[111],"obtaining":[113],"higher":[115],"quality":[116,133,139,144],"transcript.":[117],"The":[118],"two":[119],"shows":[122],"better":[123],"results":[124],"terms":[126],"agreement":[128],"experts":[130],"acoustic":[135],"modeling.":[136],"When":[137],"\u201cgold-standard\u201d":[138],"control":[140],"used,":[142],"transcripts":[147],"comes":[148],"close":[149],"NIST":[151],"published":[152],"agreement,":[154],"although":[155],"cost":[157],"doubles.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}