{"id":"https://openalex.org/W3088430977","doi":"https://doi.org/10.3233/faia200623","title":"OCR Challenges for a Latvian Pronunciation Dictionary","display_name":"OCR Challenges for a Latvian Pronunciation Dictionary","publication_year":2020,"publication_date":"2020-09-15","ids":{"openalex":"https://openalex.org/W3088430977","doi":"https://doi.org/10.3233/faia200623","mag":"3088430977"},"language":"en","primary_location":{"id":"doi:10.3233/faia200623","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200623","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200623","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200623","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083275068","display_name":"Laine Strankale","orcid":null},"institutions":[{"id":"https://openalex.org/I91123046","display_name":"University of Latvia","ror":"https://ror.org/05g3mes96","country_code":"LV","type":"education","lineage":["https://openalex.org/I91123046"]}],"countries":["LV"],"is_corresponding":true,"raw_author_name":"Laine Strankale","raw_affiliation_strings":["University of Latvia, Institute of Mathematics and Computer Science"],"affiliations":[{"raw_affiliation_string":"University of Latvia, Institute of Mathematics and Computer Science","institution_ids":["https://openalex.org/I91123046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027297183","display_name":"P\u0113teris Paikens","orcid":"https://orcid.org/0000-0002-5939-5436"},"institutions":[{"id":"https://openalex.org/I91123046","display_name":"University of Latvia","ror":"https://ror.org/05g3mes96","country_code":"LV","type":"education","lineage":["https://openalex.org/I91123046"]}],"countries":["LV"],"is_corresponding":false,"raw_author_name":"P\u0113teris Paikens","raw_affiliation_strings":["University of Latvia, Institute of Mathematics and Computer Science"],"affiliations":[{"raw_affiliation_string":"University of Latvia, Institute of Mathematics and Computer Science","institution_ids":["https://openalex.org/I91123046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083275068"],"corresponding_institution_ids":["https://openalex.org/I91123046"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16727737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9513999819755554,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9308000206947327,"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/pronunciation","display_name":"Pronunciation","score":0.8896839022636414},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.7749369144439697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7683764100074768},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7301598787307739},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6307997703552246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6012142896652222},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5777668952941895},{"id":"https://openalex.org/keywords/latvian","display_name":"Latvian","score":0.5741590261459351},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.46706634759902954},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.42574045062065125},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4191034138202667},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26564377546310425},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07811039686203003},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0736333429813385}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8896839022636414},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7749369144439697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683764100074768},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7301598787307739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6307997703552246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6012142896652222},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5777668952941895},{"id":"https://openalex.org/C2780375031","wikidata":"https://www.wikidata.org/wiki/Q9078","display_name":"Latvian","level":2,"score":0.5741590261459351},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.46706634759902954},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.42574045062065125},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4191034138202667},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26564377546310425},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07811039686203003},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0736333429813385},{"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:10.3233/faia200623","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200623","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200623","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia200623","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia200623","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA200623","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323269","display_name":"Latvijas Zin\u0101tnes Padome","ror":"https://ror.org/02ar66p97"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3088430977.pdf","grobid_xml":"https://content.openalex.org/works/W3088430977.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W112288061","https://openalex.org/W1591128439","https://openalex.org/W2164863177","https://openalex.org/W2577247581","https://openalex.org/W2577349305"],"related_works":["https://openalex.org/W4212807096","https://openalex.org/W2321033754","https://openalex.org/W2505413324","https://openalex.org/W3014057477","https://openalex.org/W2013767392","https://openalex.org/W2892857623","https://openalex.org/W3190162935","https://openalex.org/W2595338207","https://openalex.org/W1973075426","https://openalex.org/W2997809463"],"abstract_inverted_index":{"This":[0],"paper":[1],"covers":[2],"the":[3,12,26,56,79,111],"devlopment":[4],"of":[5,20,35,59,103,110,129],"a":[6,21,32,50,101,123],"custom":[7],"OCR":[8,42],"solution":[9],"based":[10],"on":[11],"Tesseract":[13],"open":[14],"source":[15],"engine":[16],"developed":[17],"for":[18,52,94,108,126,132],"digitization":[19,109],"Latvian":[22],"pronunciation":[23,27],"dictionary":[24,113],"where":[25],"data":[28],"is":[29],"described":[30],"using":[31],"large":[33],"variety":[34],"diacritic":[36],"markings":[37],"not":[38],"supported":[39],"by":[40,76],"standard":[41],"solutions.":[43],"We":[44,84],"describe":[45],"our":[46],"efforts":[47],"in":[48,78,114,122],"training":[49],"model":[51,99],"these":[53],"symbols":[54],"without":[55],"additional":[57],"support":[58],"preexisting":[60],"dictionaries":[61],"and":[62,69,82,90,119],"illustrate":[63],"how":[64],"word":[65],"error":[66,71,88],"rate":[67,72],"(WER)":[68],"character":[70],"(CER)":[73],"are":[74],"affected":[75],"changes":[77],"dataset":[80],"content":[81],"size.":[83],"also":[85],"provide":[86],"an":[87],"analysis":[89],"postulate":[91],"possible":[92],"causes":[93],"common":[95],"pitfalls.":[96],"The":[97],"resulting":[98,121],"achieved":[100],"CER":[102],"2.07%,":[104],"making":[105],"it":[106],"suitable":[107],"whole":[112],"combination":[115],"with":[116],"heuristic":[117],"post-processing":[118],"proofreading,":[120],"useful":[124],"resource":[125],"further":[127],"development":[128],"speech":[130],"technology":[131],"Latvian.":[133]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
