{"id":"https://openalex.org/W2169187092","doi":"https://doi.org/10.1109/icassp.2009.4960690","title":"Restoring punctuation and capitalization in transcribed speech","display_name":"Restoring punctuation and capitalization in transcribed speech","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2169187092","doi":"https://doi.org/10.1109/icassp.2009.4960690","mag":"2169187092"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7916/d8dj5pz0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011425224","display_name":"Agust\u0131\u0301n Gravano","orcid":"https://orcid.org/0000-0003-2812-6361"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Agustin Gravano","raw_affiliation_strings":["Department of Computer Science, Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069254823","display_name":"Martin Jansche","orcid":"https://orcid.org/0000-0003-0484-4879"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Jansche","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4741","last_page":"4744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","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/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":0.9716297388076782},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.8474015593528748},{"id":"https://openalex.org/keywords/capitalization","display_name":"Capitalization","score":0.8162274956703186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7458326816558838},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.574575662612915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5449579358100891},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5072381496429443},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48211002349853516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42783647775650024},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16624906659126282},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10037878155708313}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9716297388076782},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.8474015593528748},{"id":"https://openalex.org/C2779137862","wikidata":"https://www.wikidata.org/wiki/Q425951","display_name":"Capitalization","level":2,"score":0.8162274956703186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458326816558838},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.574575662612915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5449579358100891},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5072381496429443},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48211002349853516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42783647775650024},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16624906659126282},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10037878155708313},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2009.4960690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.8561","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.8561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.columbia.edu/speech/PaperFiles/2009/gravano_et_al_2009.pdf","raw_type":"text"},{"id":"pmh:oai:academiccommons.columbia.edu:10.7916/D8DJ5PZ0","is_oa":false,"landing_page_url":"https://doi.org/10.7916/D8DJ5PZ0","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Presentations (Communicative Events)"},{"id":"doi:10.7916/d8dj5pz0","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8dj5pz0","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.7916/d8dj5pz0","is_oa":true,"landing_page_url":"https://doi.org/10.7916/d8dj5pz0","pdf_url":null,"source":{"id":"https://openalex.org/S4306402601","display_name":"Columbia Academic Commons (Columbia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78577930","host_organization_name":"Columbia University","host_organization_lineage":["https://openalex.org/I78577930"],"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":"article-journal"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W94670513","https://openalex.org/W171402391","https://openalex.org/W1562171723","https://openalex.org/W1587490638","https://openalex.org/W2014703436","https://openalex.org/W2109664771","https://openalex.org/W2113851376","https://openalex.org/W2130784467","https://openalex.org/W2153895584","https://openalex.org/W2161274063","https://openalex.org/W2426479676","https://openalex.org/W4285719527","https://openalex.org/W6603793917","https://openalex.org/W6607019473","https://openalex.org/W6635223454","https://openalex.org/W6676373471"],"related_works":["https://openalex.org/W2250909759","https://openalex.org/W2532616038","https://openalex.org/W2624072012","https://openalex.org/W2787311093","https://openalex.org/W2057384730","https://openalex.org/W4307474317","https://openalex.org/W2008468404","https://openalex.org/W2147879411","https://openalex.org/W2132221452","https://openalex.org/W2081295016"],"abstract_inverted_index":{"Adding":[0],"punctuation":[1],"and":[2,50],"capitalization":[3],"greatly":[4],"improves":[5,73],"the":[6,33,39,51,77],"readability":[7],"of":[8,37,53],"automatic":[9],"speech":[10],"transcripts.":[11],"We":[12,31],"discuss":[13],"an":[14],"approach":[15],"for":[16],"performing":[17],"both":[18],"tasks":[19],"in":[20],"a":[21,25],"single":[22],"pass":[23],"using":[24,67],"purely":[26],"text-based":[27],"n-gram":[28,40,78],"language":[29],"model.":[30],"study":[32],"effect":[34],"on":[35],"performance":[36],"varying":[38],"order":[41,79],"(from":[42,56],"n":[43,47],"=":[44,48],"3":[45],"to":[46,59],"6)":[49],"amount":[52],"training":[54,69],"data":[55,70],"58":[57],"million":[58],"55":[60],"billion":[61],"tokens).":[62],"Our":[63],"results":[64],"show":[65],"that":[66],"larger":[68],"sets":[71],"consistently":[72],"performance,":[74],"while":[75],"increasing":[76],"does":[80],"not":[81],"help":[82],"nearly":[83],"as":[84],"much.":[85]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}