{"id":"https://openalex.org/W4319586055","doi":"https://doi.org/10.1109/iscslp57327.2022.10038277","title":"A Preliminary Study on Taiwanese OCR for Assisting Textual Database Construction from Historical Documents","display_name":"A Preliminary Study on Taiwanese OCR for Assisting Textual Database Construction from Historical Documents","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586055","doi":"https://doi.org/10.1109/iscslp57327.2022.10038277"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038277","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10038277","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5082271172","display_name":"Yuan\u2010Fu Liao","orcid":"https://orcid.org/0000-0003-0191-2178"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Fu Liao","raw_affiliation_strings":["National Yang Ming Chiao Tung University,HsinChu,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,HsinChu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033445569","display_name":"Yu-Hsuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Hsuan Huang","raw_affiliation_strings":["National Taipei University of Technology,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taipei University of Technology,Taipei,Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022501326","display_name":"Mat\u00fa\u0161 Pleva","orcid":"https://orcid.org/0000-0003-4380-0801"},"institutions":[{"id":"https://openalex.org/I183764125","display_name":"Technical University of Ko\u0161ice","ror":"https://ror.org/05xm08015","country_code":"SK","type":"education","lineage":["https://openalex.org/I183764125"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Matus Pleva","raw_affiliation_strings":["Technical University of Kosice,Ko&#x0161;ice,Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Kosice,Ko&#x0161;ice,Slovakia","institution_ids":["https://openalex.org/I183764125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080567273","display_name":"Daniel Hl\u00e1dek","orcid":"https://orcid.org/0000-0003-1148-3194"},"institutions":[{"id":"https://openalex.org/I183764125","display_name":"Technical University of Ko\u0161ice","ror":"https://ror.org/05xm08015","country_code":"SK","type":"education","lineage":["https://openalex.org/I183764125"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Daniel Hladek","raw_affiliation_strings":["Technical University of Kosice,Ko&#x0161;ice,Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Kosice,Ko&#x0161;ice,Slovakia","institution_ids":["https://openalex.org/I183764125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091093449","display_name":"Ming-Hsiang Su","orcid":"https://orcid.org/0000-0003-0633-774X"},"institutions":[{"id":"https://openalex.org/I185940356","display_name":"Soochow University","ror":"https://ror.org/05kvm7n82","country_code":"TW","type":"education","lineage":["https://openalex.org/I185940356"]},{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Ming-Hsiang Su","raw_affiliation_strings":["Soochow University,Suzhou,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,Suzhou,Taiwan","institution_ids":["https://openalex.org/I185940356","https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20959723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/1507.05717","issue":null,"first_page":"270","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9976999759674072,"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":0.992900013923645,"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/usable","display_name":"USable","score":0.84376060962677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.818867564201355},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7117534279823303},{"id":"https://openalex.org/keywords/writing-system","display_name":"Writing system","score":0.5848681926727295},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5570909976959229},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5153928995132446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40549978613853455},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39061158895492554},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.37405580282211304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32771748304367065},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16682672500610352},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13676682114601135}],"concepts":[{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.84376060962677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818867564201355},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7117534279823303},{"id":"https://openalex.org/C78148190","wikidata":"https://www.wikidata.org/wiki/Q8192","display_name":"Writing system","level":2,"score":0.5848681926727295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5570909976959229},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5153928995132446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40549978613853455},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39061158895492554},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.37405580282211304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32771748304367065},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16682672500610352},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13676682114601135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038277","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10038277","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2524643686","https://openalex.org/W2564693945","https://openalex.org/W2950477116","https://openalex.org/W2965066169","https://openalex.org/W2983383722","https://openalex.org/W3023805750","https://openalex.org/W3153529054","https://openalex.org/W3216666189","https://openalex.org/W4229030834","https://openalex.org/W4281724000","https://openalex.org/W4285160250","https://openalex.org/W4382202677","https://openalex.org/W6629717138","https://openalex.org/W6687615561","https://openalex.org/W6691371945","https://openalex.org/W6756085102","https://openalex.org/W6801347494","https://openalex.org/W6839401645","https://openalex.org/W6839838693"],"related_works":["https://openalex.org/W2982321410","https://openalex.org/W2392004567","https://openalex.org/W2046296964","https://openalex.org/W2940029036","https://openalex.org/W4388292429","https://openalex.org/W2756595502","https://openalex.org/W1991513203","https://openalex.org/W3178467699","https://openalex.org/W2347884623","https://openalex.org/W2351698706"],"abstract_inverted_index":{"Currently,":[0],"there":[1],"is":[2],"not":[3],"enough":[4],"Taiwanese":[5,21,36,58,80],"text":[6],"available":[7,94],"to":[8,15,45],"build":[9],"a":[10,51,73],"proper":[11],"language":[12],"model":[13],"(LM)":[14],"support":[16],"the":[17,34,63,66,86],"construction":[18],"of":[19,54,57,65],"emerging":[20],"automatic":[22],"speech":[23],"recognition":[24,39],"(ASR)":[25],"and":[26,82,90],"text-to-speech":[27],"(TTS)":[28],"systems.":[29],"Therefore,":[30],"this":[31],"paper":[32],"reports":[33],"first":[35],"optical":[37],"character":[38],"(OCR)":[40],"[1,":[41],"2,":[42],"3]":[43],"system":[44],"assist":[46],"human":[47],"annotators":[48],"in":[49,62,85],"converting":[50],"vast":[52],"collection":[53],"scanned":[55],"images":[56],"historical":[59],"documents":[60],"preserved":[61],"\u201cMemory":[64],"Written":[67],"Taiwanese\u201d":[68],"(MoWT)":[69],"website":[70],"[4]":[71],"into":[72],"usable":[74],"textual":[75],"database":[76],"for":[77],"building":[78],"state-of-the-art":[79],"ASR":[81],"TTS":[83],"systems":[84],"future.":[87],"Supplementary":[88],"information":[89],"replication":[91],"materials":[92],"are":[93],"on":[95],"GitHub":[96],"[5].":[97]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
