{"id":"https://openalex.org/W2395974568","doi":"https://doi.org/10.21437/slate.2009-24","title":"A self-transcribing speech corpus: collecting continuous speech with an online educational game","display_name":"A self-transcribing speech corpus: collecting continuous speech with an online educational game","publication_year":2009,"publication_date":"2009-09-03","ids":{"openalex":"https://openalex.org/W2395974568","doi":"https://doi.org/10.21437/slate.2009-24","mag":"2395974568"},"language":"en","primary_location":{"id":"doi:10.21437/slate.2009-24","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2009-24","pdf_url":"https://www.isca-archive.org/slate_2009/gruenstein09_slate.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech and Language Technology in Education (SLaTE 2009)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/slate_2009/gruenstein09_slate.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012096308","display_name":"Alexander Gruenstein","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Gruenstein","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Lab, Cambridge, MA, USA","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Lab, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048236120","display_name":"Ian McGraw","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian McGraw","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Lab, Cambridge, MA, USA","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Lab, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106819404","display_name":"Andrew M. Sutherland","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Sutherland","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Lab, Cambridge, MA, USA","Quizlet.com, Albany, CA, USA","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Lab, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Quizlet.com, Albany, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":47,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"109","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9993000030517578,"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":0.9993000030517578,"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/T11309","display_name":"Music 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/T12031","display_name":"Speech and dialogue systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8116227984428406},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6792927384376526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6776602864265442},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6371474266052246},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.6292672753334045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5388637781143188},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44189316034317017},{"id":"https://openalex.org/keywords/crowd-sourcing","display_name":"Crowd sourcing","score":0.42373210191726685},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4186943769454956},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3152514100074768},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1372784972190857},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.09166666865348816},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.062004268169403076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116227984428406},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6792927384376526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6776602864265442},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6371474266052246},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.6292672753334045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5388637781143188},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44189316034317017},{"id":"https://openalex.org/C3018396927","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowd sourcing","level":2,"score":0.42373210191726685},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4186943769454956},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3152514100074768},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1372784972190857},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.09166666865348816},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.062004268169403076},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/slate.2009-24","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2009-24","pdf_url":"https://www.isca-archive.org/slate_2009/gruenstein09_slate.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech and Language Technology in Education (SLaTE 2009)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/slate.2009-24","is_oa":true,"landing_page_url":"http://dx.doi.org/10.21437/slate.2009-24","pdf_url":"https://www.isca-archive.org/slate_2009/gruenstein09_slate.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech and Language Technology in Education (SLaTE 2009)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2395974568.pdf","grobid_xml":"https://content.openalex.org/works/W2395974568.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W178084687","https://openalex.org/W1542920136","https://openalex.org/W1970381522","https://openalex.org/W2109933326","https://openalex.org/W2111732304","https://openalex.org/W2139820289","https://openalex.org/W2141282920","https://openalex.org/W2148122154"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793","https://openalex.org/W2349468610"],"abstract_inverted_index":{"We":[0,37,82,129],"describe":[1],"a":[2,39,67,107,113],"novel":[3],"approach":[4],"to":[5,31,91],"collecting":[6],"orthographically":[7,92],"transcribed":[8],"continuous":[9],"speech":[10,30,72],"data":[11,119,136],"through":[12],"the":[13,51,76,96,118,131],"use":[14],"of":[15,41,47,115,117,133],"an":[16],"online":[17],"educational":[18],"game":[19,64],"called":[20],"Voice":[21,56],"Scatter,":[22],"in":[23,70,75,95],"which":[24,121],"players":[25],"study":[26],"flashcards":[27],"by":[28],"using":[29],"match":[32],"terms":[33],"with":[34,101],"their":[35],"definitions.":[36],"analyze":[38],"corpus":[40,77,97],"30,938":[42],"utterances,":[43],"totaling":[44],"27.63":[45],"hours":[46],"speech,":[48],"collected":[49],"during":[50],"first":[52],"22":[53],"days":[54],"that":[55,84,110],"Scatter":[57],"was":[58],"publicly":[59],"available.":[60],"Though":[61],"each":[62],"individual":[63],"covers":[65],"only":[66],"small":[68],"vocabulary,":[69],"aggregate":[71],"recognition":[73,122],"hypotheses":[74,123],"contain":[78],"21,758":[79],"distinct":[80],"words.":[81],"show":[83],"Amazon":[85],"Mechanical":[86],"Turk":[87],"can":[88,124],"be":[89,125],"used":[90],"transcribe":[93],"utterances":[94],"quickly":[98],"and":[99],"cheaply,":[100],"near-expert":[102],"accuracy.":[103],"Moreover,":[104],"we":[105],"present":[106],"filtering":[108],"technique":[109],"automatically":[111],"identifies":[112],"sub-corpus":[114],"39%":[116],"for":[120,137],"considered":[126],"human-quality":[127],"transcripts.":[128],"demonstrate":[130],"usefulness":[132],"such":[134],"self-transcribed":[135],"acoustic":[138],"model":[139],"adaptation.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
