{"id":"https://openalex.org/W3003960098","doi":"https://doi.org/10.1587/transinf.2019edp7234","title":"Automatic Construction of a Large-Scale Speech Recognition Database Using Multi-Genre Broadcast Data with Inaccurate Subtitle Timestamps","display_name":"Automatic Construction of a Large-Scale Speech Recognition Database Using Multi-Genre Broadcast Data with Inaccurate Subtitle Timestamps","publication_year":2020,"publication_date":"2020-01-31","ids":{"openalex":"https://openalex.org/W3003960098","doi":"https://doi.org/10.1587/transinf.2019edp7234","mag":"3003960098"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edp7234","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7234","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/2/E103.D_2019EDP7234/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/2/E103.D_2019EDP7234/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037088989","display_name":"Jeong\u2010Uk Bang","orcid":"https://orcid.org/0000-0002-0439-6802"},"institutions":[{"id":"https://openalex.org/I163753206","display_name":"Chungbuk National University","ror":"https://ror.org/02wnxgj78","country_code":"KR","type":"education","lineage":["https://openalex.org/I163753206"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong-Uk BANG","raw_affiliation_strings":["School of Electronics Engineering, Chungbuk National University"],"affiliations":[{"raw_affiliation_string":"School of Electronics Engineering, Chungbuk National University","institution_ids":["https://openalex.org/I163753206"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018013035","display_name":"Mu-Yeol Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mu-Yeol CHOI","raw_affiliation_strings":["Electronics and Telecommunications Research Institute"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705921","display_name":"Sanghun Kim","orcid":"https://orcid.org/0000-0002-1423-6116"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hun KIM","raw_affiliation_strings":["Electronics and Telecommunications Research Institute"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000031464","display_name":"Oh\u2010Wook Kwon","orcid":"https://orcid.org/0000-0002-5301-126X"},"institutions":[{"id":"https://openalex.org/I163753206","display_name":"Chungbuk National University","ror":"https://ror.org/02wnxgj78","country_code":"KR","type":"education","lineage":["https://openalex.org/I163753206"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Oh-Wook KWON","raw_affiliation_strings":["School of Electronics Engineering, Chungbuk National University"],"affiliations":[{"raw_affiliation_string":"School of Electronics Engineering, Chungbuk National University","institution_ids":["https://openalex.org/I163753206"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037088989"],"corresponding_institution_ids":["https://openalex.org/I163753206"],"apc_list":null,"apc_paid":null,"fwci":1.3594,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84910992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"E103.D","issue":"2","first_page":"406","last_page":"415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music and Audio Processing","score":0.9932000041007996,"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/T10860","display_name":"Speech and Audio Processing","score":0.9901000261306763,"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/subtitle","display_name":"Subtitle","score":0.9508318305015564},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.8625866174697876},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7660806179046631},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5077518224716187},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.49997687339782715},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3821133077144623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3693319857120514},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36007338762283325},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32821857929229736},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.0721055269241333}],"concepts":[{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.9508318305015564},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.8625866174697876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660806179046631},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5077518224716187},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.49997687339782715},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3821133077144623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3693319857120514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36007338762283325},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32821857929229736},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.0721055269241333},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2019edp7234","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7234","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/2/E103.D_2019EDP7234/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edp7234","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7234","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/2/E103.D_2019EDP7234/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G266350272","display_name":null,"funder_award_id":"19ZS1140","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"}],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3003960098.pdf","grobid_xml":"https://content.openalex.org/works/W3003960098.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W1494198834","https://openalex.org/W1517939602","https://openalex.org/W1631260214","https://openalex.org/W1647671624","https://openalex.org/W1975113979","https://openalex.org/W2033256038","https://openalex.org/W2161513525","https://openalex.org/W2288371874","https://openalex.org/W2289874485","https://openalex.org/W2341824394","https://openalex.org/W2510349098","https://openalex.org/W2736419256","https://openalex.org/W2745538008"],"related_works":["https://openalex.org/W2060561905","https://openalex.org/W1417711376","https://openalex.org/W1950334511","https://openalex.org/W3119551990","https://openalex.org/W2351264416","https://openalex.org/W3004133161","https://openalex.org/W4311609618","https://openalex.org/W2952626934","https://openalex.org/W4309267392","https://openalex.org/W3003960098"],"abstract_inverted_index":{"As":[0],"deep":[1],"learning-based":[2],"speech":[3,12,47,69,87,121,132,159,213],"recognition":[4],"systems":[5],"are":[6,51],"spotlighted,":[7],"the":[8,34,38,56,84,112,115,136,142,147,153,158,165,168,174,195,199],"need":[9],"for":[10,14,26,33,207],"large-scale":[11,68],"databases":[13],"acoustic":[15],"model":[16],"training":[17],"is":[18,123,149,161,205],"increasing.":[19],"Broadcast":[20],"data":[21,48,74,186,209,214],"can":[22,215],"be":[23,216],"easily":[24],"used":[25,44,124],"database":[27,70,160],"construction,":[28],"since":[29],"it":[30],"contains":[31],"transcripts":[32],"hearing":[35],"impaired.":[36],"However,":[37],"subtitle":[39,77,91,95,100,105,117,138,155,170,189],"timestamps":[40],"have":[41],"not":[42],"been":[43],"to":[45,55,65,111,125,135],"extract":[46,126],"because":[49],"they":[50],"often":[52],"inaccurate":[53,76,188],"due":[54],"inherent":[57],"characteristics":[58],"of":[59,114,130,167,184,194],"closed":[60],"captioning.":[61],"Thus,":[62],"we":[63],"propose":[64],"build":[66],"a":[67,103,109,120,127,131,181],"from":[71,146],"multi-genre":[72],"broadcast":[73,185,208],"with":[75,93,152,187,198],"timestamps.":[78],"The":[79],"proposed":[80],"method":[81,178,204],"first":[82],"extracts":[83],"most":[85],"likely":[86],"intervals":[88],"by":[89,163],"removing":[90],"texts":[92,101],"low":[94],"quality":[96],"index,":[97],"concatenating":[98],"adjacent":[99],"into":[102],"merged":[104,116,137,154,169],"text,":[106,139],"and":[107,140],"adding":[108],"margin":[110],"timestamp":[113],"text.":[118,156,176],"Next,":[119],"recognizer":[122],"hypothesis":[128,143,175],"text":[129,144,171],"segment":[133],"corresponding":[134],"then":[141],"obtained":[145],"decoder":[148],"recursively":[150],"aligned":[151],"Finally,":[157],"constructed":[162],"selecting":[164],"sub-parts":[166],"that":[172],"match":[173],"Our":[177],"successfully":[179],"refines":[180],"large":[182],"amount":[183],"timestamps,":[190],"taking":[191],"about":[192],"half":[193],"time":[196],"compared":[197],"previous":[200],"methods.":[201],"Consequently,":[202],"our":[203],"useful":[206],"processing,":[210],"where":[211],"bulk":[212],"collected":[217],"every":[218],"hour.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
