{"id":"https://openalex.org/W2077325010","doi":"https://doi.org/10.1109/asru.2011.6163988","title":"Crowd-sourcing for difficult transcription of speech","display_name":"Crowd-sourcing for difficult transcription of speech","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2077325010","doi":"https://doi.org/10.1109/asru.2011.6163988","mag":"2077325010"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2011.6163988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition &amp; Understanding","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/A5103246485","display_name":"J. D. Williams","orcid":"https://orcid.org/0000-0003-2460-9673"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason D. Williams","raw_affiliation_strings":["Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030467789","display_name":"I. Dan Melamed","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I. Dan Melamed","raw_affiliation_strings":["Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032923392","display_name":"Tirso Alonso","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tirso Alonso","raw_affiliation_strings":["Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018530526","display_name":"Barbara Hollister","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Hollister","raw_affiliation_strings":["Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113720165","display_name":"J. Wilpon","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Wilpon","raw_affiliation_strings":["Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Shannon Laboratory, AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"Shannon Laboratory, AT&T Labs - Research, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103246485"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":4.2937,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94586084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"535","last_page":"540"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.9631999731063843,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907757759094238},{"id":"https://openalex.org/keywords/crowd-sourcing","display_name":"Crowd sourcing","score":0.699325442314148},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6637046933174133},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5599798560142517},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5452499985694885},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4851565957069397},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.43820780515670776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39926666021347046},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32246243953704834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27750855684280396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907757759094238},{"id":"https://openalex.org/C3018396927","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowd sourcing","level":2,"score":0.699325442314148},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6637046933174133},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5599798560142517},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5452499985694885},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4851565957069397},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.43820780515670776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39926666021347046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32246243953704834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27750855684280396},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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":1,"locations":[{"id":"doi:10.1109/asru.2011.6163988","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2011.6163988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Automatic Speech Recognition &amp; Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W130097250","https://openalex.org/W1564634668","https://openalex.org/W1724528691","https://openalex.org/W1904457459","https://openalex.org/W1973200191","https://openalex.org/W2072271845","https://openalex.org/W2098865355","https://openalex.org/W2115915304","https://openalex.org/W2133990480","https://openalex.org/W2154624463","https://openalex.org/W2165861304","https://openalex.org/W2605421528","https://openalex.org/W6603931906","https://openalex.org/W6605306941","https://openalex.org/W6637626751","https://openalex.org/W6677378386"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"Crowd-sourcing":[0],"is":[1,29,80],"a":[2,62,66],"promising":[3],"method":[4,18,88,114],"for":[5],"fast":[6],"and":[7,52,64,142],"cheap":[8],"transcription":[9,71,140],"of":[10,13,23,43,77,94,118,134,145],"large":[11],"volumes":[12],"speech":[14,27,36],"data.":[15],"However,":[16],"this":[17],"cannot":[19],"achieve":[20],"the":[21,75,95,116,132],"accuracy":[22,76,91,117],"expert":[24],"transcribers":[25],"on":[26,83,92,104,139],"that":[28],"difficult":[30],"to":[31,69,108],"transcribe.":[32],"Faced":[33],"with":[34],"such":[35],"data,":[37,85],"we":[38],"developed":[39],"three":[40],"new":[41],"methods":[42,55,121],"crowd-sourcing,":[44],"which":[45,146],"allow":[46],"explicit":[47],"trade-offs":[48],"among":[49],"precision,":[50],"recall,":[51],"cost.":[53],"The":[54],"are:":[56],"incremental":[57],"redundancy,":[58],"treating":[59],"ASR":[60],"as":[61,126],"transcriber,":[63],"using":[65,97,122],"regression":[67],"model":[68],"predict":[70],"reliability.":[72],"Even":[73],"though":[74],"individual":[78],"crowd-workers":[79],"only":[81,98,123],"55%":[82],"our":[84,86,112],"best":[87,113],"achieves":[89],"90%":[90],"93%":[93],"utterances,":[96,111],"1.3":[99],"crowd-worker":[100],"transcriptions":[101],"per":[102],"utterance":[103],"average.":[105],"When":[106],"forced":[107],"transcribe":[109],"all":[110],"matches":[115],"previous":[119],"crowd-sourcing":[120],"one":[124],"third":[125],"many":[127],"transcriptions.":[128],"We":[129],"also":[130],"study":[131],"effects":[133],"various":[135],"task":[136],"design":[137],"factors":[138],"latency":[141],"accuracy,":[143],"some":[144],"have":[147],"not":[148],"been":[149],"reported":[150],"before.":[151]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
