{"id":"https://openalex.org/W2127540288","doi":"https://doi.org/10.1109/tasl.2008.2006654","title":"An Iterative Relative Entropy Minimization-Based Data Selection Approach for n-Gram Model Adaptation","display_name":"An Iterative Relative Entropy Minimization-Based Data Selection Approach for n-Gram Model Adaptation","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2127540288","doi":"https://doi.org/10.1109/tasl.2008.2006654","mag":"2127540288"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2006654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2006654","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/A5088302697","display_name":"Abhinav Sethy","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abhinav Sethy","raw_affiliation_strings":["Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021678540","display_name":"Panayiotis Georgiou","orcid":"https://orcid.org/0000-0002-0790-7161"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panayiotis G. Georgiou","raw_affiliation_strings":["Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal & Image Process. Inst., Univ. of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088302697"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":2.6171,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.90938194,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":"1","first_page":"13","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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":0.9993000030517578,"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/perplexity","display_name":"Perplexity","score":0.8092546463012695},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7968168258666992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7925376892089844},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7068310976028442},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.7026386260986328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5500673651695251},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.53925621509552},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5128329396247864},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49391061067581177},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.46613284945487976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45309028029441833},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.44024786353111267},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.3901022970676422},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.19173407554626465},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.1194840669631958},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09580406546592712}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8092546463012695},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7968168258666992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925376892089844},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7068310976028442},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.7026386260986328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5500673651695251},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.53925621509552},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5128329396247864},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49391061067581177},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.46613284945487976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45309028029441833},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.44024786353111267},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3901022970676422},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.19173407554626465},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.1194840669631958},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09580406546592712},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2008.2006654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2006654","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W24513791","https://openalex.org/W75470185","https://openalex.org/W97072897","https://openalex.org/W138349765","https://openalex.org/W149934508","https://openalex.org/W161909597","https://openalex.org/W1480662687","https://openalex.org/W1571931074","https://openalex.org/W1797288984","https://openalex.org/W1850668662","https://openalex.org/W2000577984","https://openalex.org/W2018560257","https://openalex.org/W2018731989","https://openalex.org/W2024490156","https://openalex.org/W2047295649","https://openalex.org/W2087596289","https://openalex.org/W2094971681","https://openalex.org/W2097089247","https://openalex.org/W2097801438","https://openalex.org/W2097927681","https://openalex.org/W2098318492","https://openalex.org/W2099111195","https://openalex.org/W2105638720","https://openalex.org/W2105830342","https://openalex.org/W2113632140","https://openalex.org/W2120084270","https://openalex.org/W2125529971","https://openalex.org/W2127602683","https://openalex.org/W2130716237","https://openalex.org/W2132024321","https://openalex.org/W2134510195","https://openalex.org/W2136504847","https://openalex.org/W2163537793","https://openalex.org/W2164666834","https://openalex.org/W2169710708","https://openalex.org/W2950186769","https://openalex.org/W6601018735","https://openalex.org/W6603931906","https://openalex.org/W6606189396","https://openalex.org/W6606586049","https://openalex.org/W6628488335","https://openalex.org/W6638218882","https://openalex.org/W6678720029","https://openalex.org/W6684299209"],"related_works":["https://openalex.org/W2132221452","https://openalex.org/W2393111077","https://openalex.org/W2151348424","https://openalex.org/W2153295945","https://openalex.org/W1577263324","https://openalex.org/W2050138804","https://openalex.org/W2125852914","https://openalex.org/W2787311093","https://openalex.org/W2169518243","https://openalex.org/W2105076537"],"abstract_inverted_index":{"Performance":[0],"of":[1,11,26,41,50,68,81,97,105,153,161],"statistical":[2],"n-gram":[3,100],"language":[4,29,111,170],"models":[5],"depends":[6],"heavily":[7],"on":[8,52,110],"the":[9,16,20,24,53,64,69,73,78,103,142,154],"amount":[10],"training":[12,21],"text":[13,22,42,70],"material":[14],"and":[15,66,127,169],"degree":[17],"to":[18,55,94,148],"which":[19],"matches":[23,102],"domain":[25,104,123],"interest.":[27,106],"The":[28],"modeling":[30],"community":[31],"is":[32],"showing":[33],"a":[34,47,89,119,128],"growing":[35],"interest":[36],"in":[37,61,159],"using":[38,114],"large":[39,129],"collections":[40],"(obtainable,":[43],"for":[44,133],"example,":[45],"from":[46,72,77],"diverse":[48],"set":[49],"resources":[51],"Internet)":[54],"supplement":[56],"sparse":[57],"in-domain":[58],"resources.":[59],"However,":[60],"most":[62],"cases":[63],"style":[65],"content":[67],"harvested":[71],"web":[74],"differs":[75],"significantly":[76],"specific":[79],"nature":[80],"these":[82],"domains.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87],"present":[88,108],"relative":[90],"entropy":[91],"based":[92],"method":[93],"select":[95],"subsets":[96],"sentences":[98],"whose":[99],"distribution":[101],"We":[107,139],"results":[109],"model":[112,171],"adaptation":[113],"two":[115],"speech":[116,156,163],"recognition":[117,157,164],"tasks:":[118],"medium":[120],"vocabulary":[121,130],"medical":[122],"doctor-patient":[124],"dialog":[125],"system":[126,132],"transcription":[131],"European":[134],"parliamentary":[135],"plenary":[136],"speeches":[137],"(EPPS).":[138],"show":[140],"that":[141],"proposed":[143],"subset":[144],"selection":[145],"scheme":[146],"leads":[147],"performance":[149],"improvements":[150],"over":[151],"state":[152],"art":[155],"systems":[158],"terms":[160],"both":[162],"word":[165],"error":[166],"rate":[167],"(WER)":[168],"perplexity":[172],"(PPL).":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}