{"id":"https://openalex.org/W4408355145","doi":"https://doi.org/10.1109/icassp49660.2025.10890531","title":"MathReader : Text-to-Speech for Mathematical Documents","display_name":"MathReader : Text-to-Speech for Mathematical Documents","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355145","doi":"https://doi.org/10.1109/icassp49660.2025.10890531"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890531","doi":"https://doi.org/10.1109/icassp49660.2025.10890531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890531","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.07088","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107294118","display_name":"Sieun Hyeon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sieun Hyeon","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088896521","display_name":"Kyudan Jung","orcid":"https://orcid.org/0000-0002-5657-7533","observed_orcids":["https://orcid.org/0000-0002-5657-7533"]},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyudan Jung","raw_affiliation_strings":["Chung-Ang University,Department of Mathematics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Mathematics","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000717294","display_name":"Nam-Joon Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam-Joon Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023354297","display_name":"Hyun Gon Ryu","orcid":"https://orcid.org/0009-0006-9799-2668","observed_orcids":["https://orcid.org/0009-0006-9799-2668"]},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Hyun Gon Ryu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024989829","display_name":"Jaeyoung Do","orcid":"https://orcid.org/0000-0003-1275-1621","observed_orcids":["https://orcid.org/0000-0003-1275-1621"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeyoung Do","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2704,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.97095147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.5238999724388123,"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"}},"topics":[{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.5238999724388123,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.28690001368522644,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.16329999268054962,"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/text-to-speech","display_name":"text-to-speech","score":0.953000009059906},{"id":"https://openalex.org/keywords/mathematical-documents","display_name":"mathematical documents","score":0.8460000157356262},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.9049999713897705},{"id":"https://openalex.org/keywords/t5-fine-tuning","display_name":"T5 fine-tuning","score":0.8939999938011169},{"id":"https://openalex.org/keywords/document-accessibility","display_name":"document accessibility","score":0.49900001287460327},{"id":"https://openalex.org/keywords/visually-impaired-users","display_name":"visually impaired users","score":0.9700000286102295},{"id":"https://openalex.org/keywords/academic-papers","display_name":"academic papers","score":0.6019999980926514},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.6380000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7728110551834106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5260210633277893},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49825620651245117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4054471254348755}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890531","doi":"https://doi.org/10.1109/icassp49660.2025.10890531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890531","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.07088","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07088","pdf_url":"https://arxiv.org/pdf/2501.07088","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/228173","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/228173","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"doi:10.48550/arxiv.2501.07088","doi":"https://doi.org/10.48550/arxiv.2501.07088","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.07088","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.07088","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.07088","pdf_url":"https://arxiv.org/pdf/2501.07088","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G116252662","display_name":null,"funder_award_id":"IITP-2024-RS-2024-00397085","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2947324332","display_name":null,"funder_award_id":"RS-2021II211343","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4475359334","display_name":null,"funder_award_id":"RS2021-II211343","funder_id":"https://openalex.org/F4320321292","funder_display_name":"Seoul National University"},{"id":"https://openalex.org/G7565319904","display_name":null,"funder_award_id":"IITP\u20102023\u2010RS\u20102023\u201000256081","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8947148644","display_name":null,"funder_award_id":"2023-RS-2023-00256081","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408355145.pdf","grobid_xml":"https://content.openalex.org/works/W4408355145.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2941064704","https://openalex.org/W2997564208","https://openalex.org/W3088711103","https://openalex.org/W3095113710","https://openalex.org/W3138516171","https://openalex.org/W3169905056","https://openalex.org/W3189734236","https://openalex.org/W4252812408","https://openalex.org/W4385823163","https://openalex.org/W4388832873","https://openalex.org/W4389027761","https://openalex.org/W4389421783","https://openalex.org/W4391020683","https://openalex.org/W4402500734","https://openalex.org/W4402954411","https://openalex.org/W4408354000","https://openalex.org/W4409362737","https://openalex.org/W6784333009","https://openalex.org/W6851724922","https://openalex.org/W7133219565"],"related_works":["https://openalex.org/W4409362737","https://openalex.org/W7129631880","https://openalex.org/W4402500734","https://openalex.org/W2613036186","https://openalex.org/W4415433560","https://openalex.org/W7221510160","https://openalex.org/W7127101251","https://openalex.org/W2070201027","https://openalex.org/W2145005674","https://openalex.org/W7097712849"],"abstract_inverted_index":{"TTS":[0,18,64,110],"(Text-to-Speech)":[1],"document":[2,65,111],"reader":[3],"from":[4,130,139],"Microsoft,":[5],"Adobe,":[6],"Apple,":[7],"and":[8,46,98,117,138],"OpenAI":[9],"have":[10],"been":[11],"serviced":[12],"worldwide.":[13],"They":[14],"provide":[15,29],"relatively":[16],"good":[17],"results":[19,31],"for":[20,32],"general":[21],"plain":[22],"text,":[23],"but":[24],"sometimes":[25],"skip":[26],"contents":[27],"or":[28],"unsatisfactory":[30],"mathematical":[33,78,124],"expressions.":[34],"This":[35,147],"is":[36,73,172],"because":[37],"most":[38],"modern":[39],"academic":[40],"papers":[41],"are":[42,50,53,167],"written":[43],"in":[44],"LaTeX,":[45],"when":[47,120],"LaTeX":[48],"formulas":[49],"compiled,":[51],"they":[52],"rendered":[54],"as":[55,71,114],"distinctive":[56],"text":[57,70],"forms":[58],"within":[59],"the":[60,69,77,81,128,153],"document.":[61],"However,":[62],"traditional":[63],"readers":[66],"output":[67],"only":[68],"it":[72],"recognized,":[74],"without":[75],"considering":[76],"meaning":[79],"of":[80],"formulas.":[82,125],"To":[83],"address":[84],"this":[85],"issue,":[86],"we":[87],"propose":[88],"MathReader,":[89],"which":[90],"effectively":[91],"integrates":[92],"OCR,":[93],"a":[94,102],"fine-tuned":[95],"T5":[96],"model,":[97],"TTS.":[99],"MathReader":[100,126],"demonstrated":[101],"lower":[103],"Word":[104],"Error":[105],"Rate":[106],"(WER)":[107],"than":[108],"existing":[109],"readers,":[112],"such":[113],"Microsoft":[115,136],"Edge":[116],"Adobe":[118,145],"Acrobat,":[119],"processing":[121],"documents":[122],"containing":[123],"reduced":[127],"WER":[129],"0.510":[131],"to":[132,135,141,144,151,160,162],"0.281":[133,142],"compared":[134,143],"Edge,":[137],"0.617":[140],"Acrobat.":[146],"will":[148],"significantly":[149],"contribute":[150],"alleviating":[152],"inconvenience":[154],"faced":[155],"by":[156],"users":[157],"who":[158,166],"want":[159],"listen":[161],"documents,":[163],"especially":[164],"those":[165],"visually":[168],"impaired.":[169],"The":[170],"code":[171],"available":[173],"at":[174],"https://github.com/hyeonsieun/MathReader.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-03-13T00:00:00"}