{"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","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890531","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/A5107294118","display_name":"Sieun Hyeon","orcid":null},"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"},"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},"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":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyun Gon Ryu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024989829","display_name":"Jaeyoung Do","orcid":"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":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7708,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84900522,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.970300018787384,"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":0.970300018787384,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7728110551834106},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5260210633277893},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49825620651245117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4054471254348755}],"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":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890531","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"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/W3189734236","https://openalex.org/W4252812408","https://openalex.org/W4385823163","https://openalex.org/W4388832873","https://openalex.org/W4389027761","https://openalex.org/W4391020683","https://openalex.org/W4408354000","https://openalex.org/W4409362737","https://openalex.org/W6784333009","https://openalex.org/W6796464841","https://openalex.org/W6851724922","https://openalex.org/W6853515095","https://openalex.org/W6859457051","https://openalex.org/W6872463079","https://openalex.org/W6872931082"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"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":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}