{"id":"https://openalex.org/W2505877856","doi":"https://doi.org/10.1145/2899475.2899478","title":"The effects of automatic speech recognition quality on human transcription latency","display_name":"The effects of automatic speech recognition quality on human transcription latency","publication_year":2016,"publication_date":"2016-04-11","ids":{"openalex":"https://openalex.org/W2505877856","doi":"https://doi.org/10.1145/2899475.2899478","mag":"2505877856"},"language":"en","primary_location":{"id":"doi:10.1145/2899475.2899478","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2899475.2899478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Web for All Conference","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/A5034136587","display_name":"Yashesh Gaur","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":"Yashesh Gaur","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063574664","display_name":"Walter S. Lasecki","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walter S. Lasecki","raw_affiliation_strings":["University of Michigan, Ann Arbor"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082603621","display_name":"Jeffrey P. Bigham","orcid":"https://orcid.org/0000-0002-2072-0625"},"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":"Jeffrey P. Bigham","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034136587"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":6.1841,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96498105,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8361324071884155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8073931932449341},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7860745191574097},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6728361248970032},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5820946097373962},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4246062934398651},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08383557200431824}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8361324071884155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073931932449341},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7860745191574097},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6728361248970032},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5820946097373962},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4246062934398651},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08383557200431824},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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:10.1145/2899475.2899478","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2899475.2899478","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Web for All Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337112","display_name":"National Institute on Disability and Rehabilitation Research","ror":"https://ror.org/021adze67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W783257918","https://openalex.org/W1514583064","https://openalex.org/W1524333225","https://openalex.org/W1524956127","https://openalex.org/W1585154421","https://openalex.org/W1968326021","https://openalex.org/W1970663544","https://openalex.org/W1971631540","https://openalex.org/W2005665592","https://openalex.org/W2010246411","https://openalex.org/W2012339105","https://openalex.org/W2015631279","https://openalex.org/W2020966112","https://openalex.org/W2035874553","https://openalex.org/W2038486467","https://openalex.org/W2055306925","https://openalex.org/W2058556535","https://openalex.org/W2072271845","https://openalex.org/W2090048052","https://openalex.org/W2095734449","https://openalex.org/W2098893679","https://openalex.org/W2104452028","https://openalex.org/W2116680608","https://openalex.org/W2127849236","https://openalex.org/W2144883443","https://openalex.org/W2148209802","https://openalex.org/W2160815625","https://openalex.org/W2250357346","https://openalex.org/W2270765880","https://openalex.org/W2289912446","https://openalex.org/W2295145241","https://openalex.org/W2295744349","https://openalex.org/W2296235715","https://openalex.org/W2296516251","https://openalex.org/W2394492257","https://openalex.org/W2408370704","https://openalex.org/W2913879771","https://openalex.org/W2963211739"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2028097510","https://openalex.org/W113247760","https://openalex.org/W1967477266","https://openalex.org/W2505877856","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2544241817"],"abstract_inverted_index":{"Transcription":[0],"makes":[1],"speech":[2,14,31,95,104,155],"accessible":[3],"to":[4,15,71,90,127],"deaf":[5],"and":[6,76,116],"hard":[7],"of":[8,13,29,84,93,139,154,182],"hearing":[9],"people.":[10],"This":[11],"conversion":[12,42],"text":[16],"is":[17,34,87,124,172,176],"still":[18,35],"done":[19],"manually":[20],"by":[21,142],"humans,":[22],"despite":[23],"high":[24,99],"cost,":[25,80],"because":[26],"the":[27,49,82,91,94,112,137,152,169],"quality":[28,92],"automated":[30],"recognition":[32,96,105,156],"(ASR)":[33],"too":[36,125],"low":[37],"in":[38],"real-world":[39],"settings.":[40],"Manual":[41],"can":[43],"require":[44],"more":[45,74],"than":[46,110],"5":[47],"times":[48],"original":[50],"audio":[51],"time,":[52],"which":[53,164],"also":[54],"introduces":[55],"significant":[56],"latency.":[57],"Giving":[58],"transcriptionists":[59,117],"ASR":[60,170],"output":[61,106,123,171],"as":[62],"a":[63,68],"starting":[64,167],"point":[65],"seems":[66],"like":[67],"reasonable":[69],"approach":[70,86],"making":[72],"humans":[73],"efficient":[75],"thereby":[77],"reducing":[78],"this":[79,85,131],"but":[81],"effectiveness":[83],"clearly":[88],"related":[89],"output.":[97,157],"At":[98],"error":[100],"rates,":[101],"fixing":[102],"inaccurate":[103,126],"may":[107,118],"take":[108],"longer":[109],"producing":[111],"transcription":[113,122],"from":[114,161],"scratch,":[115],"not":[119],"realize":[120],"when":[121],"be":[128],"useful.":[129],"In":[130],"paper,":[132],"we":[133],"empirically":[134],"explore":[135],"how":[136],"latency":[138],"transcriptions":[140],"created":[141],"participants":[143],"recruited":[144],"on":[145,151],"Amazon":[146],"Mechanical":[147],"Turk":[148],"vary":[149],"based":[150],"accuracy":[153],"We":[158],"present":[159],"results":[160],"2":[162],"studies":[163],"indicate":[165],"that":[166],"with":[168],"worse":[173],"unless":[174],"it":[175],"sufficiently":[177],"accurate":[178],"(Word":[179],"Error":[180],"Rate":[181],"under":[183],"30%).":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}