{"id":"https://openalex.org/W2120773360","doi":"https://doi.org/10.1109/icassp.2012.6288830","title":"Constructing ensembles of dissimilar acoustic models using hidden attributes of training data","display_name":"Constructing ensembles of dissimilar acoustic models using hidden attributes of training data","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2120773360","doi":"https://doi.org/10.1109/icassp.2012.6288830","mag":"2120773360"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288830","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":"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/A5102876935","display_name":"Takashi Fukuda","orcid":"https://orcid.org/0000-0002-4601-0955"},"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":false,"raw_author_name":"Takashi Fukuda","raw_affiliation_strings":["IBM Research-Tokyo, IBM Japan Limited, Japan","IBM Research - Tokyo, IBM Japan Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research-Tokyo, IBM Japan Limited, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Research - Tokyo, IBM Japan Ltd., Japan","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013412274","display_name":"Ryuki Tachibana","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":false,"raw_author_name":"Ryuki Tachibana","raw_affiliation_strings":["IBM Research-Tokyo, IBM Japan Limited, Japan","IBM Research - Tokyo, IBM Japan Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research-Tokyo, IBM Japan Limited, Japan","institution_ids":["https://openalex.org/I4210145865"]},{"raw_affiliation_string":"IBM Research - Tokyo, IBM Japan Ltd., Japan","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110218731","display_name":"Upendra V. Chaudhari","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/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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Upendra Chaudhari","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","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/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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109588257","display_name":"Puming Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"Puming Zhan","raw_affiliation_strings":["Nuance Communications, Inc., Boston, MA, USA","Nuance Communications Inc., Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc., Boston, MA, USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Nuance Communications Inc., Boston, MA, USA","institution_ids":["https://openalex.org/I1292318990"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"4141","last_page":"4144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7614173889160156},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7100186347961426},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5841826796531677},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5487426519393921},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48101291060447693},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47068363428115845},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.468847393989563},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.467360258102417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4361569285392761},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4313659369945526},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.42650938034057617},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4229735732078552},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.41922345757484436},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41859549283981323},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4012409448623657},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19092577695846558},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11372128129005432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7614173889160156},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7100186347961426},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5841826796531677},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5487426519393921},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48101291060447693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47068363428115845},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.468847393989563},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.467360258102417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4361569285392761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4313659369945526},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.42650938034057617},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4229735732078552},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.41922345757484436},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41859549283981323},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4012409448623657},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19092577695846558},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11372128129005432},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288830","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","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W184194209","https://openalex.org/W1509455084","https://openalex.org/W1571931074","https://openalex.org/W2097978681","https://openalex.org/W2103537425","https://openalex.org/W2106554350","https://openalex.org/W2108446915","https://openalex.org/W2110765229","https://openalex.org/W2117444496","https://openalex.org/W2147768505","https://openalex.org/W2158420521","https://openalex.org/W2161347627","https://openalex.org/W6634380342","https://openalex.org/W6674334065","https://openalex.org/W6682034417"],"related_works":["https://openalex.org/W2150890698","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2121652828","https://openalex.org/W3033124456"],"abstract_inverted_index":{"One":[0],"of":[1,17,30,37,58,79],"the":[2,14,38,73,105,138,147],"objectives":[3],"in":[4,23,104,114],"acoustic":[5,18,42,50,80],"modeling":[6,35],"is":[7,108,118],"to":[8,71,143],"realize":[9],"robust":[10],"statistical":[11],"models":[12,51,81,124],"against":[13],"wide":[15],"variety":[16],"conditions":[19],"that":[20,117],"are":[21,52,125],"present":[22],"real":[24],"world":[25],"environments.":[26],"As":[27],"large":[28,152],"amounts":[29],"training":[31,74],"data":[32,39,75],"become":[33],"available,":[34],"subsets":[36],"with":[40],"similar":[41],"qualities":[43],"can":[44],"be":[45],"done":[46],"accurately":[47],"and":[48,90],"multiple":[49,123],"jointly":[53],"used":[54,99],"as":[55,86,131],"a":[56,69,93,111,151],"form":[57],"system":[59,149],"combination":[60],"or":[61],"model":[62],"selection.":[63],"In":[64],"this":[65,115],"paper,":[66],"we":[67],"propose":[68],"method":[70,136],"partition":[72],"for":[76],"constructing":[77],"ensembles":[78],"using":[82,110,127],"metadata":[83,97],"attributes":[84],"such":[85,130],"SNR,":[87],"speaking":[88],"rate,":[89],"duration":[91],"via":[92],"binary":[94,102],"tree.":[95],"The":[96,121,134],"attribute":[98],"at":[100],"each":[101],"split":[103],"decision":[106],"tree":[107],"obtained":[109],"metric":[112],"proposed":[113,135],"paper":[116],"cosine-similarity":[119],"based.":[120],"resulting":[122],"combined":[126],"voting":[128],"techniques":[129],"n-best":[132],"ROVER.":[133],"improved":[137],"recognition":[139,156],"accuracy":[140],"by":[141],"up":[142],"4%":[144],"relative":[145],"over":[146],"state-of-the-art":[148],"on":[150],"vocabulary":[153],"continuous":[154],"speech":[155],"voice":[157],"search":[158],"task.":[159]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}