{"id":"https://openalex.org/W2394492257","doi":"https://doi.org/10.21437/interspeech.2015-595","title":"Using keyword spotting to help humans correct captioning faster","display_name":"Using keyword spotting to help humans correct captioning faster","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2394492257","doi":"https://doi.org/10.21437/interspeech.2015-595","mag":"2394492257"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-595","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/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":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"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":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003251887","display_name":"Yajie Miao","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":"Yajie Miao","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, 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/I4210128676","display_name":"Human Computer Interaction (Switzerland)","ror":"https://ror.org/036dv6j71","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210128676"]},{"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":["CH","US"],"is_corresponding":false,"raw_author_name":"Jeffrey P. Bigham","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","Human Computer Interaction Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Human Computer Interaction Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I4210128676","https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2829","last_page":"2833"},"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/closed-captioning","display_name":"Closed captioning","score":0.9167315363883972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8821601867675781},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7884133458137512},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.7387056946754456},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5951396226882935},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5779255628585815},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5410266518592834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.447922021150589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4371109902858734},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3396162986755371},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2411302626132965}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9167315363883972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8821601867675781},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7884133458137512},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.7387056946754456},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5951396226882935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5779255628585815},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5410266518592834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.447922021150589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4371109902858734},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3396162986755371},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2411302626132965},{"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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-595","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.699.615","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.699.615","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/%7Ejbigham/pubs/pdfs/2015/keywordspotting.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.7681","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.7681","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/%7Eymiao/pub/HumanASR.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5980875983","display_name":"HCC: Small: Collaborative Research: Real-Time Captioning by Groups of Non-Experts for Deaf and Hard of Hearing Students","funder_award_id":"1218209","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W65139299","https://openalex.org/W114193738","https://openalex.org/W151364351","https://openalex.org/W272928725","https://openalex.org/W1524333225","https://openalex.org/W1661756259","https://openalex.org/W1968326021","https://openalex.org/W1973200191","https://openalex.org/W2000590237","https://openalex.org/W2006191099","https://openalex.org/W2015688877","https://openalex.org/W2028148926","https://openalex.org/W2072271845","https://openalex.org/W2111338354","https://openalex.org/W2115915304","https://openalex.org/W2154624463","https://openalex.org/W2160815625","https://openalex.org/W2167338739","https://openalex.org/W2169384404","https://openalex.org/W2250357346","https://openalex.org/W2295744349","https://openalex.org/W2408370704","https://openalex.org/W2442329935","https://openalex.org/W3204130541"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Automatic":[0],"real-time":[1,101,170,195],"captioning":[2],"provides":[3],"immediate":[4],"and":[5,16,23,92,107,145,172],"on":[6],"de-mand":[7],"access":[8],"to":[9,67,83,111,160,166,183],"spoken":[10,192],"content":[11],"in":[12,30,37,74,137,169],"lectures":[13],"or":[14,64,122],"talks,":[15,39],"is":[17,97,105],"a":[18,58,175],"cru-cial":[19],"accommodation":[20,182],"for":[21,100,115,134,178],"deaf":[22],"hard":[24],"of":[25,33,158],"hearing":[26],"(DHH)":[27],"people.":[28,185],"However,":[29],"the":[31,50,80,87,94,109,130,135,138,147,150,156],"presence":[32],"specialized":[34],"content,":[35],"like":[36],"techni-cal":[38],"automatic":[40],"speech":[41,188],"recognition":[42],"(ASR)":[43],"still":[44],"makes":[45],"mis-takes":[46],"which":[47,61,96],"may":[48,173],"render":[49],"output":[51,140],"incomprehensible.":[52],"In":[53],"this":[54,180],"paper,":[55],"we":[56],"introduce":[57],"new":[59],"approach,":[60],"allows":[62,108],"audience":[63],"crowd":[65,81,196],"workers,":[66],"quickly":[68,164],"correct":[69],"errors":[70],"that":[71],"they":[72],"spot":[73],"ASR":[75,88,139,151],"output.":[76,152],"Prior":[77],"approaches":[78],"required":[79],"worker":[82,110],"manu-ally":[84],"\u201cedit":[85],"\u201d":[86],"hypothesis":[89],"by":[90],"selecting":[91],"replacing":[93],"text,":[95],"not":[98],"suitable":[99],"scenarios.":[102],"Our":[103,153],"approach":[104],"faster":[106],"simply":[112],"type":[113],"corrections":[114],"misrecognized":[116],"words":[117],"as":[118,120],"soon":[119],"he":[121],"she":[123],"spots":[124],"them.":[125],"The":[126],"sys-tem":[127],"then":[128],"finds":[129],"most":[131],"likely":[132],"position":[133],"correction":[136],"using":[141],"keyword":[142],"search":[143],"(KWS)":[144],"stitches":[146],"word":[148],"into":[149],"work":[154],"demonstrates":[155],"potential":[157],"computation":[159],"incorporate":[161],"human":[162],"input":[163],"enough":[165],"be":[167,174],"usable":[168],"scenarios,":[171],"better":[176],"method":[177],"providing":[179],"vital":[181],"DHH":[184],"Index":[186],"Terms:":[187],"recognition,":[189],"human-computer":[190],"interac-tion,":[191],"term":[193],"detection,":[194],"sourcing.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
