{"id":"https://openalex.org/W2062752744","doi":"https://doi.org/10.1109/tasl.2011.2159594","title":"Bilingual Experiments on Automatic Recovery of Capitalization and Punctuation of Automatic Speech Transcripts","display_name":"Bilingual Experiments on Automatic Recovery of Capitalization and Punctuation of Automatic Speech Transcripts","publication_year":2012,"publication_date":"2012-01-31","ids":{"openalex":"https://openalex.org/W2062752744","doi":"https://doi.org/10.1109/tasl.2011.2159594","mag":"2062752744"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2159594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2159594","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","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/A5090633243","display_name":"Fernando Batista","orcid":"https://orcid.org/0000-0002-1075-0177"},"institutions":[{"id":"https://openalex.org/I110026055","display_name":"Iscte \u2013 Instituto Universit\u00e1rio de Lisboa","ror":"https://ror.org/014837179","country_code":"PT","type":"education","lineage":["https://openalex.org/I110026055"]},{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Fernando Batista","raw_affiliation_strings":["Instituto Universit\u00e1rio de Lisboa, (ISCTE-IUL), Lisboa, Portugal","Spoken Language Laboratory, INESC-ID, Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Universit\u00e1rio de Lisboa, (ISCTE-IUL), Lisboa, Portugal","institution_ids":["https://openalex.org/I110026055"]},{"raw_affiliation_string":"Spoken Language Laboratory, INESC-ID, Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045429958","display_name":"Helena Moniz","orcid":"https://orcid.org/0000-0003-0900-6938"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Helena Moniz","raw_affiliation_strings":["FLUL/CLUL, University of Lisbon, Lisboa, Portugal","Spoken Language Laboratory, INESC-ID, Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FLUL/CLUL, University of Lisbon, Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]},{"raw_affiliation_string":"Spoken Language Laboratory, INESC-ID, Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054590402","display_name":"Isabel Trancoso","orcid":"https://orcid.org/0000-0001-5874-6313"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I4210154254","display_name":"Instituto Superior de Tecnologias Avan\u00e7adas","ror":"https://ror.org/04hzbg791","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210154254"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Isabel Trancoso","raw_affiliation_strings":["IST, Lisboa, Portugal","Spoken Language Laboratory, INESC-ID, Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IST, Lisboa, Portugal","institution_ids":["https://openalex.org/I4210154254"]},{"raw_affiliation_string":"Spoken Language Laboratory, INESC-ID, Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061593183","display_name":"Nuno Mamede","orcid":"https://orcid.org/0000-0001-6033-158X"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I4210154254","display_name":"Instituto Superior de Tecnologias Avan\u00e7adas","ror":"https://ror.org/04hzbg791","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210154254"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Mamede","raw_affiliation_strings":["IST, Lisboa, Portugal","Spoken Language Laboratory, INESC-ID, Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IST, Lisboa, Portugal","institution_ids":["https://openalex.org/I4210154254"]},{"raw_affiliation_string":"Spoken Language Laboratory, INESC-ID, Lisboa, Portugal","institution_ids":["https://openalex.org/I121345201"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.3007,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.97311046,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"20","issue":"2","first_page":"474","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9994999766349792,"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/punctuation","display_name":"Punctuation","score":0.9810225367546082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7623555064201355},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7111843228340149},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6571526527404785},{"id":"https://openalex.org/keywords/capitalization","display_name":"Capitalization","score":0.5765028595924377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5450487732887268},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4759123921394348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46176356077194214},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.44807884097099304},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3539149761199951}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9810225367546082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623555064201355},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7111843228340149},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6571526527404785},{"id":"https://openalex.org/C2779137862","wikidata":"https://www.wikidata.org/wiki/Q425951","display_name":"Capitalization","level":2,"score":0.5765028595924377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5450487732887268},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4759123921394348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46176356077194214},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.44807884097099304},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3539149761199951},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2011.2159594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2159594","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:repositorio.iscte-iul.pt:10071/7049","is_oa":false,"landing_page_url":"http://hdl.handle.net/10071/7049","pdf_url":null,"source":{"id":"https://openalex.org/S7407055197","display_name":"Reposit\u00f3rio do ISCTE-IUL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W94670513","https://openalex.org/W123007672","https://openalex.org/W171402391","https://openalex.org/W182831726","https://openalex.org/W192736094","https://openalex.org/W206998472","https://openalex.org/W616758433","https://openalex.org/W649502068","https://openalex.org/W1504308419","https://openalex.org/W1534924771","https://openalex.org/W1562171723","https://openalex.org/W1571969069","https://openalex.org/W1587490638","https://openalex.org/W1600738028","https://openalex.org/W1626209120","https://openalex.org/W1631260214","https://openalex.org/W1986748706","https://openalex.org/W2014703436","https://openalex.org/W2048679005","https://openalex.org/W2082456878","https://openalex.org/W2084480693","https://openalex.org/W2085621450","https://openalex.org/W2092269560","https://openalex.org/W2096175520","https://openalex.org/W2096389830","https://openalex.org/W2105126865","https://openalex.org/W2109886208","https://openalex.org/W2113029696","https://openalex.org/W2113851376","https://openalex.org/W2123343069","https://openalex.org/W2125557774","https://openalex.org/W2130784467","https://openalex.org/W2139828426","https://openalex.org/W2145182234","https://openalex.org/W2146688305","https://openalex.org/W2149510916","https://openalex.org/W2153804780","https://openalex.org/W2161274063","https://openalex.org/W2166128510","https://openalex.org/W2169187092","https://openalex.org/W2170381724","https://openalex.org/W2398074191","https://openalex.org/W2426479676","https://openalex.org/W2785349534","https://openalex.org/W2884262036","https://openalex.org/W2949108231","https://openalex.org/W3139713519","https://openalex.org/W3163940969","https://openalex.org/W4230961366","https://openalex.org/W4237784457","https://openalex.org/W4285719527","https://openalex.org/W4296022989","https://openalex.org/W6603793917","https://openalex.org/W6607019473","https://openalex.org/W6608560374","https://openalex.org/W6635223454","https://openalex.org/W6674650171","https://openalex.org/W6682780409","https://openalex.org/W6684467545","https://openalex.org/W6684796585","https://openalex.org/W6747435310","https://openalex.org/W6842763099"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2181793145","https://openalex.org/W1992814554","https://openalex.org/W2067802667"],"abstract_inverted_index":{"This":[0],"paper":[1,137],"focuses":[2],"on":[3,41,205],"the":[4,36,71,74,96,104,115,121,125,133,139,157,196,247,255],"tasks":[5,32],"of":[6,73,180,251],"recovering":[7],"capitalization":[8,105,116],"and":[9,55,63,80,86,127,148,163,186,218],"punctuation":[10,134,143,168,220],"marks":[11,253],"from":[12,171],"texts":[13],"without":[14],"that":[15,94,114,201],"information,":[16],"such":[17],"as":[18],"spoken":[19],"transcripts,":[20],"produced":[21],"by":[22,89,120],"automatic":[23,64],"speech":[24,75],"recognition":[25,76],"systems.":[26],"These":[27],"two":[28],"practical":[29],"rich":[30],"transcription":[31],"were":[33,50,66,153],"performed":[34],"using":[35],"same":[37],"discriminative":[38],"approach,":[39],"based":[40],"maximum":[42],"entropy,":[43],"suitable":[44],"for":[45,103,111,155,160,215,227,231],"on-the-fly":[46],"usage.":[47],"Reported":[48],"experiments":[49],"conducted":[51],"both":[52,112,216,219],"over":[53],"Portuguese":[54],"English":[56],"broadcast":[57],"news":[58],"data.":[59,129],"Both":[60],"force":[61],"aligned":[62],"transcripts":[65],"used,":[67],"allowing":[68],"to":[69,246],"measure":[70],"impact":[72],"errors.":[77],"Capitalized":[78],"words":[79],"named":[81],"entities":[82],"are":[83,87,241],"intrinsically":[84],"related,":[85],"influenced":[88],"time":[90],"variation":[91],"effects.":[92],"For":[93],"reason,":[95],"so-called":[97],"language":[98],"dynamics":[99],"have":[100],"been":[101],"addressed":[102],"task.":[106],"Language":[107],"adaptation":[108],"results":[109,159,223],"indicate,":[110],"languages,":[113],"performance":[117],"is":[118,235],"affected":[119],"temporal":[122],"distance":[123],"between":[124],"training":[126],"testing":[128],"In":[130],"what":[131],"regards":[132],"task,":[135],"this":[136],"covers":[138],"three":[140],"most":[141],"frequent":[142],"marks:":[144],"full":[145,161,228],"stop,":[146],"comma,":[147],"question":[149,232,252],"marks.":[150],"Different":[151],"methods":[152],"explored":[154],"improving":[156],"baseline":[158],"stop":[162],"comma.":[164],"The":[165,175,190,208],"first":[166,197],"uses":[167],"information":[169],"extracted":[170],"large":[172],"written":[173],"corpora.":[174,256],"second":[176,209],"applies":[177],"different":[178],"levels":[179],"linguistic":[181],"structure,":[182],"including":[183],"lexical,":[184],"prosodic,":[185],"speaker":[187],"related":[188],"features.":[189,207],"comma":[191],"detection":[192],"improved":[193],"significantly":[194],"in":[195,254],"method,":[198],"thus":[199],"indicating":[200],"it":[202],"depends":[203],"more":[204],"lexical":[206],"method":[210],"provided":[211],"even":[212],"better":[213],"results,":[214],"languages":[217],"marks,":[221,233],"best":[222],"being":[224],"achieved":[225],"mainly":[226],"stop.":[229],"As":[230],"there":[234],"a":[236],"small":[237,249],"gain,":[238],"but":[239],"differences":[240],"not":[242],"very":[243],"significant,":[244],"due":[245],"relatively":[248],"number":[250]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}
