{"id":"https://openalex.org/W2893243126","doi":"https://doi.org/10.1109/taslp.2018.2871755","title":"Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition","display_name":"Evolution-Strategy-Based Automation of System Development for High-Performance Speech Recognition","publication_year":2018,"publication_date":"2018-09-24","ids":{"openalex":"https://openalex.org/W2893243126","doi":"https://doi.org/10.1109/taslp.2018.2871755","mag":"2893243126"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2871755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2871755","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM 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/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, Yokohama, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1942-7250","affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Yokohama, 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, Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Yokohama, 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, Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Yokohama, 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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Duh","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3104,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.85550881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"27","issue":"1","first_page":"77","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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/T10320","display_name":"Neural Networks and Applications","score":0.9916999936103821,"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":0.9886999726295471,"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":0.8291110396385193},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7008479833602905},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6723804473876953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5284568667411804},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5182837843894958},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.5030342936515808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4919678866863251},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48954614996910095},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.48404592275619507},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46046870946884155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4111219644546509},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08475616574287415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8291110396385193},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7008479833602905},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6723804473876953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5284568667411804},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5182837843894958},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5030342936515808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4919678866863251},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48954614996910095},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.48404592275619507},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46046870946884155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4111219644546509},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08475616574287415},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/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/taslp.2018.2871755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2871755","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4319357441","display_name":"Constraint Free Training of Speech Recognition Systems Based on Full Bayes Modeling","funder_award_id":"17K20001","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320315072","display_name":"Mitsubishi Electric Research Laboratories","ror":null},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"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/W2008499862","https://openalex.org/W2046932483","https://openalex.org/W2062227835","https://openalex.org/W2083296885","https://openalex.org/W2090861223","https://openalex.org/W2099201756","https://openalex.org/W2115167570","https://openalex.org/W2117671523","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/W2151965738","https://openalex.org/W2160088187","https://openalex.org/W2160815625","https://openalex.org/W2164960030","https://openalex.org/W2166843422","https://openalex.org/W2192203593","https://openalex.org/W2208154600","https://openalex.org/W2288471100","https://openalex.org/W2290689761","https://openalex.org/W2514741789","https://openalex.org/W2587108411","https://openalex.org/W2587221786","https://openalex.org/W2594529350","https://openalex.org/W2949264490","https://openalex.org/W3007384386","https://openalex.org/W4205130185","https://openalex.org/W4211049957","https://openalex.org/W4252003911","https://openalex.org/W6624019940","https://openalex.org/W6631362777","https://openalex.org/W6631864531","https://openalex.org/W6675200109","https://openalex.org/W6677498713","https://openalex.org/W6678911119","https://openalex.org/W6679429981","https://openalex.org/W6682262322","https://openalex.org/W6726109732","https://openalex.org/W6733545517","https://openalex.org/W6734593296"],"related_works":["https://openalex.org/W2794103424","https://openalex.org/W1996530509","https://openalex.org/W3028317537","https://openalex.org/W2389515972","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"The":[0],"state-of-the-art":[1],"large":[2,70,118,143],"vocabulary":[3,71,144],"speech":[4,72,145],"recognition":[5,23,73,114,146],"systems":[6,115,147],"consist":[7],"of":[8,33,67,87,112,123,134],"several":[9],"components":[10,35],"including":[11],"hidden":[12],"Markov":[13],"model":[14,102],"and":[15,30,100,110],"deep":[16],"neural":[17],"network.":[18],"To":[19,57],"realize":[20],"the":[21,28,46,59,65,76,85,88,90,105,113,132,135],"highest":[22],"performance,":[24],"numerous":[25],"meta-parameters":[26,66],"specifying":[27],"designs":[29],"training":[31,109],"setups":[32],"these":[34,55],"must":[36],"be":[37],"optimized.":[38],"A":[39],"prominent":[40],"obstacle":[41],"in":[42,53],"system":[43,74,91],"development":[44],"is":[45,92],"laborious":[47],"effort":[48],"required":[49],"by":[50,138],"human":[51],"experts":[52],"tuning":[54],"meta-parameters.":[56],"automate":[58],"process,":[60],"we":[61,120],"propose":[62],"to":[63],"tune":[64],"a":[68,80],"whole":[69],"using":[75],"evolution":[77],"strategy":[78],"with":[79],"multi-objective":[81],"Pareto":[82],"optimization.":[83],"As":[84],"result":[86],"evolution,":[89],"optimized":[93],"for":[94,142],"both":[95],"low":[96],"word":[97],"error":[98],"rate":[99],"compact":[101],"size.":[103],"Since":[104],"approach":[106,137],"requires":[107],"repeated":[108],"evaluation":[111],"that":[116],"require":[117],"computation,":[119],"make":[121],"use":[122],"parallel":[124],"computation":[125],"on":[126],"cloud":[127],"computers.":[128],"Experimental":[129],"results":[130],"show":[131],"effectiveness":[133],"proposed":[136],"discovering":[139],"appropriate":[140],"configuration":[141],"automatically.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}