{"id":"https://openalex.org/W2963796169","doi":"https://doi.org/10.1109/icassp.2018.8462656","title":"Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection","display_name":"Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2963796169","doi":"https://doi.org/10.1109/icassp.2018.8462656","mag":"2963796169"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5044135870","display_name":"Taku Kala","orcid":null},"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":true,"raw_author_name":"Taku Kala","raw_affiliation_strings":["Tokyo Institute of Technology, School of Engineering, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, School of Engineering, Kanagawa, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","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, School of Engineering, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, School of Engineering, Kanagawa, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044135870"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":1.5335,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.87733976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5759","last_page":"5763"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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":0.9957000017166138,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8805621862411499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8528439998626709},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6887778043746948},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.662469208240509},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5586771368980408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.541361927986145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5393298864364624},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48542460799217224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4631110727787018},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43843013048171997},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07112070918083191}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8805621862411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8528439998626709},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6887778043746948},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.662469208240509},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5586771368980408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.541361927986145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5393298864364624},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48542460799217224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4631110727787018},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43843013048171997},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07112070918083191},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W134081589","https://openalex.org/W197872364","https://openalex.org/W272928725","https://openalex.org/W1524333225","https://openalex.org/W1588359339","https://openalex.org/W1990005421","https://openalex.org/W2087006792","https://openalex.org/W2095271936","https://openalex.org/W2098220176","https://openalex.org/W2100969003","https://openalex.org/W2119717200","https://openalex.org/W2124558353","https://openalex.org/W2131342762","https://openalex.org/W2138537392","https://openalex.org/W2146871184","https://openalex.org/W2155004026","https://openalex.org/W2155027007","https://openalex.org/W2169895393","https://openalex.org/W2257979135","https://openalex.org/W2403553999","https://openalex.org/W2696558042","https://openalex.org/W2963295373","https://openalex.org/W2964043796","https://openalex.org/W3007384386","https://openalex.org/W3139377883","https://openalex.org/W4298857966","https://openalex.org/W6605361347","https://openalex.org/W6607938559","https://openalex.org/W6610089544","https://openalex.org/W6631362777","https://openalex.org/W6635151359","https://openalex.org/W6637967152","https://openalex.org/W6640373744","https://openalex.org/W6672565315","https://openalex.org/W6679429981","https://openalex.org/W6682262322","https://openalex.org/W6683204974","https://openalex.org/W6692846177","https://openalex.org/W6713597360","https://openalex.org/W6792155000"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912","https://openalex.org/W2930320701"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,34,48,68],"recognition":[2,8,158],"(ASR)":[3],"systems":[4,18,111],"have":[5],"achieved":[6],"high":[7],"performance":[9,15,159],"for":[10,36,66,70,109,141],"several":[11,142],"tasks.":[12,61],"However,":[13],"the":[14,22,44,85,94,114,123,153,157],"of":[16,27,31,46,122],"such":[17],"is":[19,43,52],"dependent":[20],"on":[21,113],"tremendously":[23],"costly":[24],"development":[25],"work":[26],"preparing":[28],"vast":[29],"amounts":[30],"task-matched":[32],"transcribed":[33],"data":[35,69],"supervised":[37],"training.":[38],"The":[39,50,134,148],"key":[40],"problem":[41],"here":[42],"cost":[45,51],"transcribing":[47,67],"data.":[49],"repeatedly":[53],"required":[54],"to":[55,87,161],"support":[56],"new":[57,60,139],"languages":[58],"and":[59,79,145],"Assuming":[62],"broad":[63],"network":[64],"services":[65],"many":[71],"users,":[72],"a":[73,104,119,128,138],"system":[74],"would":[75],"become":[76],"more":[77,80],"self-sufficient":[78],"useful":[81],"if":[82],"it":[83],"possessed":[84],"ability":[86],"learn":[88],"from":[89,93],"very":[90],"light":[91],"feedback":[92],"users":[95],"without":[96],"annoying":[97],"them.":[98],"In":[99],"this":[100],"paper,":[101],"we":[102,125],"propose":[103,127],"general":[105],"reinforcement":[106,131],"learning":[107,132],"framework":[108,136],"ASR":[110],"based":[112],"policy":[115],"gradient":[116],"method.":[117,133],"As":[118],"particular":[120],"instance":[121],"framework,":[124],"also":[126],"hypothesis":[129],"selection-based":[130],"proposed":[135,154],"provides":[137],"view":[140],"existing":[143],"training":[144],"adaptation":[146],"methods.":[147],"experimental":[149],"results":[150],"show":[151],"that":[152],"method":[155],"improves":[156],"compared":[160],"unsupervised":[162],"adaptation.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}