{"id":"https://openalex.org/W2396251197","doi":"https://doi.org/10.21437/interspeech.2012-568","title":"Automating crowd-supervised learning for spoken language systems","display_name":"Automating crowd-supervised learning for spoken language systems","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2396251197","doi":"https://doi.org/10.21437/interspeech.2012-568","mag":"2396251197"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5048236120","display_name":"Ian McGraw","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ian McGraw","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052585866","display_name":"Scott Cyphers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scott Cyphers","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035867340","display_name":"Panupong Pasupat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panupong Pasupat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627504","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-3163-3420"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingjing Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","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":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2474","last_page":"2477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9998999834060669,"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":0.9998999834060669,"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/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8789709806442261},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6699890494346619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6319179534912109},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.6234641671180725},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6090049147605896},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5990076065063477},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5333414673805237},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5195094347000122},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.4680499732494354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46327492594718933},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42859119176864624},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39710134267807007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8789709806442261},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6699890494346619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6319179534912109},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6234641671180725},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6090049147605896},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5990076065063477},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5333414673805237},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5195094347000122},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.4680499732494354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46327492594718933},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42859119176864624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39710134267807007},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.258.7359","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.258.7359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://groups.csail.mit.edu/sls/publications/2012/McGraw-Interspeech12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W81773097","https://openalex.org/W1970381522","https://openalex.org/W1973200191","https://openalex.org/W2090755665","https://openalex.org/W2111732304","https://openalex.org/W2143280940","https://openalex.org/W2161181481","https://openalex.org/W2172501646","https://openalex.org/W2185757438","https://openalex.org/W2295092504","https://openalex.org/W2295531324","https://openalex.org/W2403947200"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W1494910745","https://openalex.org/W2114358883"],"abstract_inverted_index":{"Spoken":[0],"language":[1,72],"systems":[2],"often":[3],"rely":[4],"on":[5,68],"static":[6],"speech":[7,76],"recognizers.":[8],"When":[9],"the":[10,44,56,69],"underlying":[11],"models":[12],"are":[13],"improved":[14],"on-the-fly,":[15],"training":[16,38,57],"is":[17,48],"usually":[18],"performed":[19],"using":[20],"unsupervised":[21],"methods.":[22],"In":[23],"this":[24],"work,":[25],"we":[26,46,64],"explore":[27],"an":[28,86],"alternative":[29],"approach":[30],"that":[31],"uses":[32],"human":[33],"computation":[34],"to":[35,50],"provide":[36],"crowd-supervised":[37],"of":[39,74],"a":[40,75,79,93],"deployed":[41],"system.":[42],"Although":[43],"framework":[45],"describe":[47],"applicable":[49],"any":[51],"stochastic":[52],"model":[53,73],"for":[54],"which":[55],"data":[58],"can":[59,90],"be":[60],"generated":[61],"by":[62],"non-experts,":[63],"demonstrate":[65],"its":[66],"utility":[67],"lexicon":[70],"and":[71],"recognizer":[77],"in":[78,98],"cinema":[80],"voicesearch":[81],"domain.":[82],"We":[83,108],"show":[84],"how":[85,111],"initially":[87],"shaky":[88],"system":[89],"achieve":[91],"over":[92],"10":[94],"%":[95],"absolute":[96],"improvement":[97],"word":[99],"error":[100],"rate":[101],"(WER)":[102],"\u2013":[103],"entirely":[104],"without":[105],"expert":[106],"intervention.":[107],"then":[109],"analyze":[110],"these":[112],"gains":[113],"were":[114],"made.":[115],"1.":[116]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}