{"id":"https://openalex.org/W2288471100","doi":"https://doi.org/10.1109/asru.2015.7404852","title":"Automation of system building for state-of-the-art large vocabulary speech recognition using evolution strategy","display_name":"Automation of system building for state-of-the-art large vocabulary speech recognition using evolution strategy","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2288471100","doi":"https://doi.org/10.1109/asru.2015.7404852","mag":"2288471100"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463708","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0002-9741-5573"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070418792","display_name":"Kevin Duh","orcid":"https://orcid.org/0000-0001-8107-4383"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kevin Duh","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"610","last_page":"616"},"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":0.9965000152587891,"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":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.7802712917327881},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6570782661437988},{"id":"https://openalex.org/keywords/cma-es","display_name":"CMA-ES","score":0.633902370929718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5611119270324707},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5518133640289307},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48914578557014465},{"id":"https://openalex.org/keywords/evolution-strategy","display_name":"Evolution strategy","score":0.47008681297302246},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.423194944858551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42136114835739136},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41152840852737427},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.1690903604030609},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10151398181915283},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08323153853416443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802712917327881},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6570782661437988},{"id":"https://openalex.org/C205555498","wikidata":"https://www.wikidata.org/wiki/Q505588","display_name":"CMA-ES","level":4,"score":0.633902370929718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5611119270324707},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5518133640289307},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48914578557014465},{"id":"https://openalex.org/C207002847","wikidata":"https://www.wikidata.org/wiki/Q2912857","display_name":"Evolution strategy","level":3,"score":0.47008681297302246},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.423194944858551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42136114835739136},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41152840852737427},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.1690903604030609},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10151398181915283},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08323153853416443},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2015.7404852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W878889913","https://openalex.org/W1524333225","https://openalex.org/W1529817821","https://openalex.org/W1576660662","https://openalex.org/W1579744901","https://openalex.org/W1582482241","https://openalex.org/W1746819321","https://openalex.org/W1801780804","https://openalex.org/W1932968309","https://openalex.org/W1970789124","https://openalex.org/W2008499862","https://openalex.org/W2046932483","https://openalex.org/W2083296885","https://openalex.org/W2090861223","https://openalex.org/W2099201756","https://openalex.org/W2115167570","https://openalex.org/W2126105956","https://openalex.org/W2131241448","https://openalex.org/W2131342762","https://openalex.org/W2133750237","https://openalex.org/W2135153490","https://openalex.org/W2138537392","https://openalex.org/W2142027531","https://openalex.org/W2142416747","https://openalex.org/W2148154194","https://openalex.org/W2151965738","https://openalex.org/W2158069733","https://openalex.org/W2160088187","https://openalex.org/W2160815625","https://openalex.org/W2164960030","https://openalex.org/W2166843422","https://openalex.org/W2184045248","https://openalex.org/W2208154600","https://openalex.org/W3007384386","https://openalex.org/W4205130185","https://openalex.org/W4211049957","https://openalex.org/W6624019940","https://openalex.org/W6631362777","https://openalex.org/W6631864531","https://openalex.org/W6675200109","https://openalex.org/W6678911119","https://openalex.org/W6679429981","https://openalex.org/W6682262322"],"related_works":["https://openalex.org/W1492325323","https://openalex.org/W1579744901","https://openalex.org/W2510724351","https://openalex.org/W3087341323","https://openalex.org/W2465356436","https://openalex.org/W2552260697","https://openalex.org/W2078076985","https://openalex.org/W2592891920","https://openalex.org/W2072153706","https://openalex.org/W2734610626"],"abstract_inverted_index":{"When":[0],"building":[1],"a":[2,19,52,103,110],"state-of-the-art":[3],"speech":[4,40,143,156],"recognition":[5,41,144],"system,":[6,112],"the":[7,30,44,90,97,141,147],"laborious":[8],"effort":[9],"required":[10],"by":[11,121],"human":[12],"experts":[13],"in":[14,140],"tuning":[15],"numerous":[16],"parameters":[17],"remains":[18],"prominent":[20],"obstacle.":[21],"The":[22,134],"goal":[23],"of":[24,70,92],"this":[25],"paper":[26],"is":[27,73,76,138],"to":[28,34,59,82],"automate":[29],"process.":[31],"We":[32,86],"propose":[33],"tune":[35],"DNN-HMM":[36],"based":[37],"large":[38,154],"vocabulary":[39,155],"systems":[42,58,117,124],"using":[43,96],"covariance":[45],"matrix":[46],"adaptation":[47],"evolution":[48],"strategy":[49],"(CMA-ES)":[50],"with":[51,102,118,125],"multi-objective":[53],"Pareto":[54],"optimization.":[55],"This":[56],"optimizes":[57],"achieve":[60],"both":[61],"high-accuracy":[62],"and":[63,79,123],"compact":[64],"model":[65,128],"size.":[66],"An":[67],"additional":[68],"advantage":[69],"our":[71,113],"approach":[72,114],"that":[74],"it":[75],"efficiently":[77],"parallelizable":[78],"easily":[80],"adapted":[81],"cloud":[83],"computing":[84],"services.":[85],"performed":[87],"experiments":[88],"on":[89],"Corpus":[91],"Spontaneous":[93],"Japanese":[94,153],"(CSJ)":[95],"TSUBAME":[98],"2.5":[99],"supercomputer.":[100],"Compared":[101],"strong":[104],"manually":[105],"tuned":[106],"configuration":[107],"borrowed":[108],"from":[109],"similar":[111],"automatically":[115],"discovered":[116],"lower":[119],"WER":[120,132],"0.48%,":[122],"59%":[126],"smaller":[127],"size":[129],"while":[130],"keeping":[131],"constant.":[133],"optimized":[135],"training":[136],"script":[137],"released":[139],"Kaldi":[142],"toolkit":[145],"as":[146],"first":[148],"publicly":[149],"available":[150],"recipe":[151],"for":[152],"recognition.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}