{"id":"https://openalex.org/W51547150","doi":null,"title":"Hub4 Language Modeling Using Domain Interpolation and Data Clustering","display_name":"Hub4 Language Modeling Using Domain Interpolation and Data Clustering","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W51547150","mag":"51547150"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.4423","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.4423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-speech.sri.com/cgi-bin/run-distill?ftp:papers/darpa97-hub4-lm.ps.gz","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5103540001","display_name":"Fuliang Weng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuliang Weng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X","observed_orcids":["https://orcid.org/0000-0002-9925-905X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5104349809","display_name":"Ananth Sankar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ananth Sankar","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":0.3945,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71444115,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/clustering","display_name":"clustering","score":0.7900000214576721},{"id":"https://openalex.org/keywords/language-model-adaptation","display_name":"language model adaptation","score":0.8240000009536743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.5849999785423279},{"id":"https://openalex.org/keywords/perplexity-reduction","display_name":"perplexity reduction","score":0.8040000200271606},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.9129999876022339},{"id":"https://openalex.org/keywords/switchboard","display_name":"switchboards","score":0.8009999990463257}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9814209342002869},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7581143379211426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7535743117332458},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7078434824943542},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6246750354766846},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6195358037948608},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.566006600856781},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.545890748500824},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5389725565910339},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4769674241542816},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47671622037887573},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4704674184322357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4687766134738922},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.415915310382843},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12774759531021118},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12726187705993652},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.4423","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.4423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-speech.sri.com/cgi-bin/run-distill?ftp:papers/darpa97-hub4-lm.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.26.1359","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.1359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nist.gov/speech/publications/darpa97/ps/weng1.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.55.9379","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.55.9379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.speech.sri.com/pub/papers/darpa97-hub4-lm.ps","raw_type":"text"},{"id":"mag:51547150","doi":null,"is_oa":false,"landing_page_url":"https://www.sri.com/sites/default/files/publications/hub4_language_modeling_using_domain_interpolation_and_data.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2030610192","https://openalex.org/W2097599384","https://openalex.org/W2134237567","https://openalex.org/W2155388323","https://openalex.org/W2166637769","https://openalex.org/W2734606845"],"related_works":["https://openalex.org/W1698486872","https://openalex.org/W1578724066","https://openalex.org/W192460080","https://openalex.org/W7095124447","https://openalex.org/W2394619680","https://openalex.org/W20484969","https://openalex.org/W142799313","https://openalex.org/W3190540921","https://openalex.org/W82861581","https://openalex.org/W2147451362"],"abstract_inverted_index":{"In":[0,41],"SRI's":[1],"language":[2,26,112,121],"modeling":[3],"experiments":[4],"for":[5,49],"the":[6,25,30,35,42,50,59,70,81,86,124],"Hub4":[7,19,53,62,82],"domain,":[8],"three":[9],"basic":[10],"approaches":[11,116,139],"were":[12],"pursued:":[13],"interpolating":[14,85],"multiple":[15],"models":[16,122],"estimated":[17],"from":[18,89],"and":[20,33,58,75,99,132],"non-Hub4":[21],"training":[22,56,65,77],"data,":[23,78],"adapting":[24,34,120],"model":[27],"(LM)":[28],"to":[29,37,108,123],"focus":[31,130],"conditions,":[32,131],"LM":[36,135],"different":[38,129],"topic":[39],"types.":[40],"first":[43],"approach,":[44],"we":[45,92],"built":[46],"separate":[47],"LMs":[48],"closely":[51],"transcribed":[52,61],"material":[54,63],"(acoustic":[55],"transcripts)":[57],"loosely":[60],"(LM":[64],"data),":[66],"as":[67,69],"well":[68],"NorthAmerican":[71],"Business":[72],"News":[73],"(NABN)":[74],"Switchboard":[76],"projected":[79],"onto":[80],"vocabulary.":[83],"By":[84],"probabilities":[87],"obtained":[88,93],"these":[90],"models,":[91],"a":[94,100,109],"20%":[95],"reduction":[96,102,142],"in":[97,103,143],"perplexity":[98],"1.8%":[101],"word":[104],"error":[105],"rate,":[106],"compared":[107],"baseline":[110],"Hub4-only":[111],"model.":[113],"Two":[114],"adaptation":[115],"are":[117],"also":[118],"described:":[119],"speech":[125],"styles":[126],"correlated":[127],"with":[128],"building":[133],"cluster-specific":[134],"mixtures.":[136],"These":[137],"two":[138],"give":[140],"some":[141],"perpl...":[144]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2016-06-24T00:00:00"}