{"id":"https://openalex.org/W2135241496","doi":"https://doi.org/10.1109/icassp.2012.6288828","title":"N-best entropy based data selection for acoustic modeling","display_name":"N-best entropy based data selection for acoustic modeling","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2135241496","doi":"https://doi.org/10.1109/icassp.2012.6288828","mag":"2135241496"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5028857766","display_name":"Nobuyasu Itoh","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP","US"],"is_corresponding":true,"raw_author_name":"Nobuyasu Itoh","raw_affiliation_strings":["IBM Research-Tokyo, IBM Japan Limited, Yamato, Japan","IBM Res.-Tokyo, IBM Japan Ltd., Yamato, Japan"],"affiliations":[{"raw_affiliation_string":"IBM Research-Tokyo, IBM Japan Limited, Yamato, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Res.-Tokyo, IBM Japan Ltd., Yamato, Japan","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Thomas J. Watson Research Center Yorktown Heights, NY 10598, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Research Center Yorktown Heights, NY 10598, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014629661","display_name":"Dan Jiang","orcid":"https://orcid.org/0000-0003-4735-479X"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Dan Ning Jiang","raw_affiliation_strings":["IBM Research China, Beijing, China","IBM Research - China, #19A, Zhongguancun Software Park, Haidian District, Beijing, China 100193"],"affiliations":[{"raw_affiliation_string":"IBM Research China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM Research - China, #19A, Zhongguancun Software Park, Haidian District, Beijing, China 100193","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620306","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0001-7701-234X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["IBM Research China, Beijing, China","IBM Research - China, #19A, Zhongguancun Software Park, Haidian District, Beijing, China 100193"],"affiliations":[{"raw_affiliation_string":"IBM Research China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM Research - China, #19A, Zhongguancun Software Park, Haidian District, Beijing, China 100193","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Thomas J. Watson Research Center Yorktown Heights, NY 10598, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Thomas J. Watson Research Center Yorktown Heights, NY 10598, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028857766"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":4.0118,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93924143,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"40","issue":null,"first_page":"4133","last_page":"4136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9998000264167786,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9998000264167786,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9975000023841858,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9947999715805054,"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/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.7242408394813538},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7231926321983337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6989538669586182},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6072230935096741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5591872930526733},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5568888783454895},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5429924726486206},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5429903864860535},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.48695430159568787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39665138721466064},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3852296471595764},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3568018078804016},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23169350624084473},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16302132606506348}],"concepts":[{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.7242408394813538},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7231926321983337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6989538669586182},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6072230935096741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591872930526733},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5568888783454895},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5429924726486206},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5429903864860535},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.48695430159568787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39665138721466064},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3852296471595764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3568018078804016},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23169350624084473},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16302132606506348},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W108892041","https://openalex.org/W2027167280","https://openalex.org/W2034537249","https://openalex.org/W2095629250","https://openalex.org/W2124338691","https://openalex.org/W2127499922","https://openalex.org/W2139453310","https://openalex.org/W2152748974","https://openalex.org/W2161482971","https://openalex.org/W2167122806","https://openalex.org/W2171671120","https://openalex.org/W2594610113","https://openalex.org/W3149836819","https://openalex.org/W6604379684","https://openalex.org/W6682296883"],"related_works":["https://openalex.org/W3159631231","https://openalex.org/W4306248409","https://openalex.org/W4211213551","https://openalex.org/W2332151799","https://openalex.org/W2062728131","https://openalex.org/W1824075546","https://openalex.org/W2103926897","https://openalex.org/W2101250918","https://openalex.org/W4376143407","https://openalex.org/W2894406327"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,29,58,91,101],"strategy":[4],"for":[5,60],"efficiently":[6],"selecting":[7,20,41,61],"informative":[8],"data":[9,62],"from":[10],"large":[11],"corpora":[12],"of":[13,70,85],"untranscribed":[14],"speech.":[15],"Confidence-based":[16],"selection":[17,110,119,142],"methods":[18],"(i.e.,":[19],"utterances":[21,42,99],"we":[22,56,81],"are":[23],"least":[24],"confident":[25],"about)":[26],"have":[27],"been":[28],"popular":[30],"approach,":[31],"though":[32],"they":[33],"only":[34],"look":[35],"at":[36,64],"the":[37,75,83,133],"top":[38],"hypothesis":[39,66,72],"when":[40],"and":[43,123,127],"tend":[44],"to":[45,95],"select":[46],"outliers,":[47],"therefore,":[48],"not":[49],"always":[50],"improving":[51],"overall":[52],"recognition":[53],"accuracy.":[54],"Alternatively,":[55],"propose":[57],"method":[59],"looking":[63],"competing":[65],"by":[67,74,87],"computing":[68],"entropy":[69,108,125],"N-best":[71,107],"decoded":[73],"baseline":[76],"acoustic":[77],"model.":[78],"In":[79],"addition":[80],"address":[82],"issue":[84],"outliers":[86],"calculating":[88],"how":[89],"representative":[90],"specific":[92],"utterance":[93],"is":[94,143,150],"all":[96],"other":[97,117],"unselected":[98],"via":[100],"tf-idf":[102,129],"score.":[103],"Experiments":[104],"show":[105],"that":[106,128],"based":[109,122,130],"(%relative":[111,136],"5.8":[112],"in":[113],"400-hour":[114],"corpus)":[115],"outperformed":[116],"conventional":[118],"strategies;":[120],"confidence":[121],"lattice":[124],"based,":[126],"representativeness":[131],"improved":[132],"model":[134,147],"further":[135],"6.2).":[137],"A":[138],"comparison":[139],"with":[140],"random":[141],"also":[144],"presented.":[145],"Finally":[146],"size":[148],"impact":[149],"discussed.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}