{"id":"https://openalex.org/W2136780519","doi":"https://doi.org/10.1145/1322391.1322392","title":"Web resources for language modeling in conversational speech recognition","display_name":"Web resources for language modeling in conversational speech recognition","publication_year":2007,"publication_date":"2007-12-01","ids":{"openalex":"https://openalex.org/W2136780519","doi":"https://doi.org/10.1145/1322391.1322392","mag":"2136780519"},"language":"en","primary_location":{"id":"doi:10.1145/1322391.1322392","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1322391.1322392","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on 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/A5109934165","display_name":"Ivan Bulyko","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ivan Bulyko","raw_affiliation_strings":["BBN Technologies, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BBN Technologies, Cambridge, MA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mari Ostendorf","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067041166","display_name":"Man-Hung Siu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Manhung Siu","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110640042","display_name":"Tim Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tim Ng","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["SRI International and the International Computer Science Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International and the International Computer Science Institute","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076222573","display_name":"\u00d6zg\u00fcr \u00c7etin","orcid":"https://orcid.org/0000-0003-2365-0316"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"\u00d6zg\u00fcr \u00c7etin","raw_affiliation_strings":["International Computer Science Institute","[International Computer Science Institute]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"[International Computer Science Institute]","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109934165"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.7158,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97558051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"5","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9933000206947327,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.8785139918327332},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6540085077285767},{"id":"https://openalex.org/keywords/sublanguage","display_name":"Sublanguage","score":0.614983320236206},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5944682359695435},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5689846873283386},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.5429626703262329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4733579158782959},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3808644115924835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37088513374328613},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20243272185325623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8785139918327332},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6540085077285767},{"id":"https://openalex.org/C2776411971","wikidata":"https://www.wikidata.org/wiki/Q17141398","display_name":"Sublanguage","level":2,"score":0.614983320236206},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5944682359695435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5689846873283386},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.5429626703262329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4733579158782959},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3808644115924835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37088513374328613},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20243272185325623},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1322391.1322392","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1322391.1322392","pdf_url":null,"source":{"id":"https://openalex.org/S200945739","display_name":"ACM Transactions on Speech and Language Processing","issn_l":"1550-4875","issn":["1550-4875","1550-4883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Speech and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-19327","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-19327","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[{"id":"https://openalex.org/G2777985142","display_name":null,"funder_award_id":"FP6-506811","funder_id":"https://openalex.org/F4320334962","funder_display_name":"Sixth Framework Programme"},{"id":"https://openalex.org/G8246102066","display_name":null,"funder_award_id":"MDA972-02-C-0038","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320334962","display_name":"Sixth Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W11314411","https://openalex.org/W75470185","https://openalex.org/W82457882","https://openalex.org/W116332155","https://openalex.org/W122657243","https://openalex.org/W144133755","https://openalex.org/W158414620","https://openalex.org/W161909597","https://openalex.org/W177307080","https://openalex.org/W187516025","https://openalex.org/W193643080","https://openalex.org/W199541590","https://openalex.org/W295271566","https://openalex.org/W324111278","https://openalex.org/W1631260214","https://openalex.org/W1665921526","https://openalex.org/W1713240683","https://openalex.org/W1733633583","https://openalex.org/W1773803948","https://openalex.org/W1797288984","https://openalex.org/W1850668662","https://openalex.org/W1926502259","https://openalex.org/W2000577984","https://openalex.org/W2014516359","https://openalex.org/W2025157233","https://openalex.org/W2043693083","https://openalex.org/W2049633694","https://openalex.org/W2068017609","https://openalex.org/W2093585241","https://openalex.org/W2094971681","https://openalex.org/W2105830342","https://openalex.org/W2107682024","https://openalex.org/W2109426048","https://openalex.org/W2111305191","https://openalex.org/W2115407392","https://openalex.org/W2121147010","https://openalex.org/W2123938550","https://openalex.org/W2124416056","https://openalex.org/W2126414663","https://openalex.org/W2130806807","https://openalex.org/W2133486044","https://openalex.org/W2137227096","https://openalex.org/W2147182112","https://openalex.org/W2148231634","https://openalex.org/W2148798929","https://openalex.org/W2158195707","https://openalex.org/W2163704482","https://openalex.org/W2164107060","https://openalex.org/W2164666834","https://openalex.org/W2166637769","https://openalex.org/W2168515284","https://openalex.org/W2169518243","https://openalex.org/W2435251607","https://openalex.org/W2603415636","https://openalex.org/W2603454388","https://openalex.org/W2915722758","https://openalex.org/W2964076070","https://openalex.org/W3010185159","https://openalex.org/W6608044769","https://openalex.org/W6636811518","https://openalex.org/W6637497015","https://openalex.org/W6638218882","https://openalex.org/W6674010617","https://openalex.org/W6681733276"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1581527501","https://openalex.org/W1887737739","https://openalex.org/W2887321929","https://openalex.org/W2384978429","https://openalex.org/W1986338539","https://openalex.org/W3107474891","https://openalex.org/W1517743118","https://openalex.org/W2501432536","https://openalex.org/W2136780519"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"a":[3,13,61],"methodology":[4],"for":[5],"collecting":[6],"text":[7],"from":[8,29],"the":[9,32,46,52,66,90],"Web":[10,94],"to":[11,36,51],"match":[12],"target":[14],"sublanguage":[15],"both":[16],"in":[17,60,71],"style":[18],"(register)":[19],"and":[20,38,106,110,113],"topic.":[21],"Unlike":[22],"other":[23],"work":[24],"that":[25],"estimates":[26],"n-gram":[27,53],"statistics":[28],"page":[30],"counts,":[31],"approach":[33],"here":[34],"is":[35],"select":[37],"filter":[39],"documents,":[40],"which":[41],"provides":[42],"more":[43],"control":[44],"over":[45],"type":[47],"of":[48,63,74,93,102],"material":[49],"contributing":[50],"counts.":[54],"The":[55],"data":[56,82],"can":[57,84],"be":[58,85],"used":[59],"variety":[62],"ways;":[64],"here,":[65],"different":[67],"sources":[68],"are":[69],"combined":[70],"two":[72],"types":[73],"mixture":[75],"models.":[76],"Focusing":[77],"on":[78,96],"conversational":[79],"speech":[80],"where":[81],"collection":[83],"quite":[86],"costly,":[87],"experiments":[88],"demonstrate":[89],"positive":[91],"impact":[92],"collections":[95],"several":[97],"tasks":[98],"with":[99],"varying":[100],"amounts":[101],"data,":[103],"including":[104],"Mandarin":[105],"English":[107,111],"telephone":[108],"conversations":[109],"meetings":[112],"lectures.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}