{"id":"https://openalex.org/W2572048724","doi":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-062","title":"Automatic Transcription of Historical Newsprint by Leveraging the Kaldi Speech Recognition Toolkit","display_name":"Automatic Transcription of Historical Newsprint by Leveraging the Kaldi Speech Recognition Toolkit","publication_year":2016,"publication_date":"2016-02-17","ids":{"openalex":"https://openalex.org/W2572048724","doi":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-062","mag":"2572048724"},"language":"en","primary_location":{"id":"doi:10.2352/issn.2470-1173.2016.17.drr-062","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-062","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-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/A5067979421","display_name":"Patrick Schone","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Schone","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058847496","display_name":"Alan Cannaday","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alan Cannaday","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005541766","display_name":"Seth Stewart","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seth Stewart","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109360943","display_name":"Rachael Day","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rachael Day","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005563696","display_name":"Jeremy Schone","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeremy Schone","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8662,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85070131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"28","issue":"17","first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.882099986076355,"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":0.882099986076355,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.8586000204086304,"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":0.829800009727478,"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/newsprint","display_name":"Newsprint","score":0.8986971378326416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7536515593528748},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.7484169602394104},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6784343123435974},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5530868768692017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5347458720207214},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5229457020759583},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47679996490478516},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44911208748817444},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4334474205970764},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4256868362426758},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3733241558074951},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21685689687728882},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07617127895355225}],"concepts":[{"id":"https://openalex.org/C157714500","wikidata":"https://www.wikidata.org/wiki/Q187046","display_name":"Newsprint","level":3,"score":0.8986971378326416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536515593528748},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.7484169602394104},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6784343123435974},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5530868768692017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5347458720207214},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5229457020759583},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47679996490478516},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44911208748817444},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4334474205970764},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4256868362426758},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3733241558074951},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21685689687728882},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07617127895355225},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"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/C2779251873","wikidata":"https://www.wikidata.org/wiki/Q80294","display_name":"Cellulose","level":2,"score":0.0},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2352/issn.2470-1173.2016.17.drr-062","is_oa":false,"landing_page_url":"https://doi.org/10.2352/issn.2470-1173.2016.17.drr-062","pdf_url":null,"source":{"id":"https://openalex.org/S4210227276","display_name":"Electronic Imaging","issn_l":"2470-1173","issn":["2470-1173"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronic Imaging","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2490496563","https://openalex.org/W2312453581","https://openalex.org/W2019318116","https://openalex.org/W2040402785","https://openalex.org/W2314884184","https://openalex.org/W2381552593","https://openalex.org/W2347719083","https://openalex.org/W2323839547","https://openalex.org/W2378348141","https://openalex.org/W2992316075"],"abstract_inverted_index":{"We":[0,109,137,167],"present":[1],"a":[2,17,128],"method":[3],"for":[4,11,22],"transcribing":[5],"historical":[6,43],"newsprint":[7,44],"images.":[8],"To":[9],"begin,":[10],"training":[12],"and":[13,59,76,105,126,155],"evaluation,":[14],"we":[15,48,70,77],"created":[16],"corpus":[18],"of":[19,37,41,62,94,113,123,131,141,146,183],"human-generated":[20],"transcripts":[21],"almost":[23],"38,000":[24],"image":[25,97],"snippets":[26,133],"which":[27,101,175],"contains":[28],"nearly":[29],"five":[30],"million":[31],"words.":[32],"This":[33],"may":[34],"be":[35],"one":[36],"the":[38,56,63,92,147,162,181],"largest":[39],"corpora":[40],"transcribed":[42],"ever":[45],"created.":[46],"Then,":[47],"developed":[49],"our":[50,84,114,139,170],"automatic":[51],"transcription":[52],"process":[53,171],"by":[54,134],"leveraging":[55],"pattern":[57],"recognition":[58,66],"statistical":[60],"components":[61,82,90],"state-of-the-art":[64,103],"speech":[65],"toolkit,":[67],"Kaldi.":[68],"Specifically,":[69],"modified":[71],"its":[72],"language":[73],"model":[74],"behavior":[75],"replaced":[78],"Kaldi's":[79],"speech-to-features":[80],"transformation":[81],"with":[83],"own":[85],"image-to-features":[86],"process.":[87],"Our":[88],"replacement":[89],"include":[91],"use":[93],"word":[95],"partials;":[96],"rotation;":[98],"line":[99],"segmentation":[100],"extends":[102],"methods;":[104],"customized":[106],"feature":[107],"generation.":[108],"conduct":[110],"two":[111],"evaluations":[112,143],"technology:":[115],"(a)":[116],"an":[117],"evaluation":[118,130],"based":[119],"on":[120],"random":[121],"selections":[122],"newspaper":[124,132],"snippets;":[125],"(b)":[127],"diachronic":[129],"time":[135],"frame.":[136],"compare":[138],"results":[140],"these":[142,184],"to":[144,161,178],"those":[145],"commercial":[148],"engines":[149],"ABBYY":[150],"Fine":[151],"Reader":[152],"Version":[153],"12":[154],"OmniPage":[156],"18,":[157],"as":[158,160],"well":[159],"freely":[163],"available":[164],"system,":[165],"Tesseract.":[166],"demonstrate":[168],"that":[169],"typically":[172],"yields":[173],"accuracies":[174,182],"are":[176],"comparable":[177],"or":[179],"exceed":[180],"other":[185],"engines.":[186]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}