{"id":"https://openalex.org/W4408355095","doi":"https://doi.org/10.1109/icassp49660.2025.10890316","title":"Decreasing Word Error Rates in Paragraph Handwritten Text Recognition with Synthetic Data","display_name":"Decreasing Word Error Rates in Paragraph Handwritten Text Recognition with Synthetic Data","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355095","doi":"https://doi.org/10.1109/icassp49660.2025.10890316"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5034873733","display_name":"Elaine Chew","orcid":"https://orcid.org/0000-0002-8342-1024"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Ernest Yu-Kai Chew","raw_affiliation_strings":["Nanyang Technological University,College of Computing and Data Science,Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,College of Computing and Data Science,Singapore,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047970310","display_name":"Adams Wai\u2010Kin Kong","orcid":"https://orcid.org/0000-0002-9728-9511"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Adams Wai-Kin Kong","raw_affiliation_strings":["Nanyang Technological University,College of Computing and Data Science,Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,College of Computing and Data Science,Singapore,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111947901","display_name":"Lim Joo-Hwee","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Lim Joo-Hwee","raw_affiliation_strings":["A*STAR,Institute for Infocomm Research,Singapore,Singapore"],"affiliations":[{"raw_affiliation_string":"A*STAR,Institute for Infocomm Research,Singapore,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034873733"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.6381,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88378243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9991999864578247,"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":0.9991999864578247,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9413999915122986,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9279999732971191,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/paragraph","display_name":"Paragraph","score":0.8991366624832153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7864038944244385},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6760132312774658},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.660807728767395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6281127333641052},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6211666464805603},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5544836521148682},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35063397884368896},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1619248390197754},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.05612802505493164}],"concepts":[{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.8991366624832153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864038944244385},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6760132312774658},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.660807728767395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6281127333641052},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6211666464805603},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5544836521148682},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35063397884368896},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1619248390197754},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.05612802505493164},{"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:10.1109/icassp49660.2025.10890316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1982907973","https://openalex.org/W2018970719","https://openalex.org/W2020407556","https://openalex.org/W2021043164","https://openalex.org/W2060746081","https://openalex.org/W2147393756","https://openalex.org/W2152928267","https://openalex.org/W2343052201","https://openalex.org/W2400491034","https://openalex.org/W2573601984","https://openalex.org/W2577122925","https://openalex.org/W2786429113","https://openalex.org/W2895359355","https://openalex.org/W2904714269","https://openalex.org/W2962784628","https://openalex.org/W2963250244","https://openalex.org/W2964325005","https://openalex.org/W2984703264","https://openalex.org/W3003428515","https://openalex.org/W3003915459","https://openalex.org/W3025872686","https://openalex.org/W3031548983","https://openalex.org/W3034726763","https://openalex.org/W3082022228","https://openalex.org/W3098985395","https://openalex.org/W3112478873","https://openalex.org/W3173630418","https://openalex.org/W3199055417","https://openalex.org/W4254139502","https://openalex.org/W4288049477","https://openalex.org/W4382202677","https://openalex.org/W4386083087","https://openalex.org/W6636915900","https://openalex.org/W6674330103","https://openalex.org/W6704241340","https://openalex.org/W6768080748","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2296205523","https://openalex.org/W2405439032","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"Handwritten":[0],"Text":[1],"Recognition":[2],"(HTR)":[3],"faces":[4],"a":[5,46,83,102],"persistent":[6],"challenge":[7],"with":[8,82,101,142],"the":[9,14,19,56,67,76,109,116,123,129],"scarcity":[10],"of":[11,21,78],"data":[12,86],"at":[13],"paragraph":[15,68],"level,":[16],"arising":[17],"from":[18],"difficulty":[20],"acquiring":[22],"diverse,":[23],"cost-efficient,":[24],"and":[25,40,58,139],"cleanly":[26],"labeled":[27],"datasets":[28],"for":[29,119],"training.":[30],"As":[31],"such,":[32],"works":[33],"in":[34,45,99],"HTR":[35],"leverage":[36],"segmentation,":[37],"regularization":[38],"techniques,":[39],"language":[41],"modeling":[42],"to":[43,66,74],"excel":[44],"low-data":[47],"environment.":[48],"While":[49],"synthetic":[50,85,97],"generation":[51],"methods":[52,118],"gain":[53],"traction":[54],"on":[55,122,132],"word":[57],"line-level":[59],"recognition,":[60],"this":[61],"success":[62],"has":[63],"not":[64],"translated":[65],"level.":[69],"Hence,":[70],"our":[71,96],"work":[72],"seeks":[73],"mimic":[75],"nuances":[77],"paragraph-level":[79],"text":[80],"images":[81],"custom":[84],"engine":[87],"using":[88,95],"Wikipedia":[89],"texts.":[90],"Experiments":[91],"show":[92,128],"that":[93],"by":[94],"dataset":[98],"tandem":[100],"simple":[103],"encoder-decoder":[104],"Transformer,":[105],"we":[106,127],"can":[107,135],"achieve":[108],"best":[110],"Word":[111],"Error":[112],"Rate":[113],"(WER)":[114],"amongst":[115],"state-of-the-art":[117],"handwriting":[120],"recognition":[121],"IAM":[124],"dataset.":[125],"Additionally,":[126],"model":[130],"pretrained":[131],"English":[133],"texts":[134,141],"also":[136],"recognize":[137],"French":[138],"German":[140],"minimal":[143],"finetuning.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}