{"id":"https://openalex.org/W2096750468","doi":"https://doi.org/10.1109/icassp.2005.1415184","title":"Maximum Entropy Based Generic Filter for Language Model Adaptation","display_name":"Maximum Entropy Based Generic Filter for Language Model Adaptation","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2096750468","doi":"https://doi.org/10.1109/icassp.2005.1415184","mag":"2096750468"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100894532","display_name":"Dong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Speech Research Group, Microsoft Research Limited, Redmond, WA, USA","Speech Research Group, Microsoft Research, Redmond, WA. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Group, Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Speech Research Group, Microsoft Research, Redmond, WA. USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113252773","display_name":"M. Mahajan","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Mahajan","raw_affiliation_strings":["Speech Research Group, Microsoft Research Limited, Redmond, WA, USA","Speech Research Group, Microsoft Research, Redmond, WA. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Group, Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Speech Research Group, Microsoft Research, Redmond, WA. USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016350517","display_name":"Peter Mau","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Mau","raw_affiliation_strings":["Speech Research Group, Microsoft Research Limited, Redmond, WA, USA","Speech Research Group, Microsoft Research, Redmond, WA. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Group, Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Speech Research Group, Microsoft Research, Redmond, WA. USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Acero","raw_affiliation_strings":["Speech Research Group, Microsoft Research Limited, Redmond, WA, USA","Speech Research Group, Microsoft Research, Redmond, WA. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Research Group, Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Speech Research Group, Microsoft Research, Redmond, WA. USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.7328,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68449573,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"597","last_page":"600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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":0.9889000058174133,"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/dictation","display_name":"Dictation","score":0.7883197665214539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7511978149414062},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6931103467941284},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6275054812431335},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5751590728759766},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5639415979385376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.516314685344696},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5031561255455017},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4974255859851837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44626399874687195},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43311983346939087},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38275614380836487},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11273378133773804}],"concepts":[{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.7883197665214539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511978149414062},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6931103467941284},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6275054812431335},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5751590728759766},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5639415979385376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.516314685344696},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5031561255455017},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4974255859851837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44626399874687195},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43311983346939087},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38275614380836487},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11273378133773804},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/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/icassp.2005.1415184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.124.5180","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.124.5180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/srg/papers/2005-dongyu-icassp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W17500809","https://openalex.org/W114579992","https://openalex.org/W1934019294","https://openalex.org/W1996903695","https://openalex.org/W2001792610","https://openalex.org/W2096175520","https://openalex.org/W2096375461","https://openalex.org/W2161482971","https://openalex.org/W3149836819","https://openalex.org/W6604782888","https://openalex.org/W6640267182","https://openalex.org/W6674650171"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2047632477","https://openalex.org/W2129812225","https://openalex.org/W2523799048"],"abstract_inverted_index":{"Language":[0],"model":[1],"(LM)":[2],"adaptation":[3,81,126],"has":[4],"been":[5],"shown":[6],"to":[7,72],"be":[8],"very":[9],"important":[10],"in":[11,18,27,138],"reducing":[12],"the":[13,28,52,62,80,85,88,104,107,112,115,135],"word":[14],"error":[15],"rate":[16],"(WER)":[17],"task":[19],"specific":[20],"speech":[21],"recognition":[22],"systems.":[23],"Adaptation":[24],"data":[25,59,82],"collected":[26],"real":[29],"world,":[30],"however,":[31],"usually":[32],"contain":[33],"large":[34],"amounts":[35],"of":[36,76,87,106,114],"non-dictated":[37,77],"text,":[38],"such":[39],"as":[40],"email":[41,141],"headers,":[42],"long":[43],"URL,":[44],"code":[45],"fragments,":[46],"included":[47],"reply,":[48],"signature,":[49],"etc.,":[50],"that":[51,93,111],"user":[53],"never":[54],"dictates.":[55],"Adapting":[56],"with":[57],"these":[58],"may":[60],"corrupt":[61],"LM.":[63],"We":[64,91,102],"propose":[65],"a":[66,74],"maximum":[67],"entropy":[68],"(MaxEnt)":[69],"based":[70],"filter":[71,96,116],"remove":[73],"variety":[75],"words":[78],"from":[79],"and":[83,100,109,129],"improve":[84],"effectiveness":[86],"LM":[89,125,137],"adaptation.":[90],"argue":[92],"this":[94],"generic":[95],"is":[97],"language":[98],"independent":[99],"efficient.":[101],"describe":[103],"design":[105],"filter,":[108],"show":[110],"use":[113],"can":[117],"give":[118],"us":[119],"10%":[120],"relative":[121,131],"WER":[122,132],"reduction":[123,133],"over":[124,134],"without":[127],"filtering,":[128],"22%":[130],"unadapted":[136],"an":[139],"English":[140],"dictation":[142],"task.":[143]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}