{"id":"https://openalex.org/W2920831951","doi":"https://doi.org/10.23919/apsipa.2018.8659527","title":"Reward Only Training of Encoder-Decoder Digit Recognition Systems Based on Policy Gradient Methods","display_name":"Reward Only Training of Encoder-Decoder Digit Recognition Systems Based on Policy Gradient Methods","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2920831951","doi":"https://doi.org/10.23919/apsipa.2018.8659527","mag":"2920831951"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659527","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102322933","display_name":"Yilong Peng","orcid":"https://orcid.org/0009-0004-9680-9863"},"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":"Yilong Peng","raw_affiliation_strings":["Tokyo Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003049061","display_name":"Hayato Shibata","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":false,"raw_author_name":"Hayato Shibata","raw_affiliation_strings":["Tokyo Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","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"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102322933"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18966691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1934","last_page":"1939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9988999962806702,"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":0.8270218372344971},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6713016033172607},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6433889865875244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5864578485488892},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5608981847763062},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5311896800994873},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5220070481300354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5146435499191284},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4761471748352051},{"id":"https://openalex.org/keywords/numerical-digit","display_name":"Numerical digit","score":0.4613852798938751},{"id":"https://openalex.org/keywords/digit-recognition","display_name":"Digit recognition","score":0.4274210035800934},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.383304238319397},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11247703433036804},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.10866525769233704},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07292726635932922}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270218372344971},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6713016033172607},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6433889865875244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5864578485488892},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5608981847763062},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5311896800994873},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5220070481300354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5146435499191284},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4761471748352051},{"id":"https://openalex.org/C94957134","wikidata":"https://www.wikidata.org/wiki/Q82990","display_name":"Numerical digit","level":2,"score":0.4613852798938751},{"id":"https://openalex.org/C2984784707","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Digit recognition","level":3,"score":0.4274210035800934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.383304238319397},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11247703433036804},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.10866525769233704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07292726635932922},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/apsipa.2018.8659527","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:00897:0004123263","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100791978","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2095271936","https://openalex.org/W2098220176","https://openalex.org/W2102113734","https://openalex.org/W2119717200","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2138537392","https://openalex.org/W2151965738","https://openalex.org/W2155004026","https://openalex.org/W2155027007","https://openalex.org/W2156718681","https://openalex.org/W2157331557","https://openalex.org/W2180816288","https://openalex.org/W2342662072","https://openalex.org/W2402144811","https://openalex.org/W2736601468","https://openalex.org/W2786608204","https://openalex.org/W2953384591","https://openalex.org/W2962765220","https://openalex.org/W2963144852","https://openalex.org/W2963266252","https://openalex.org/W2963295373","https://openalex.org/W2963641140","https://openalex.org/W2963727906","https://openalex.org/W2963796169","https://openalex.org/W2963980299","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3007384386","https://openalex.org/W4230563027","https://openalex.org/W6640373744","https://openalex.org/W6675365184","https://openalex.org/W6679436768","https://openalex.org/W6682262322","https://openalex.org/W6682888085","https://openalex.org/W6683204974","https://openalex.org/W6686002079","https://openalex.org/W6692846177","https://openalex.org/W6704571135","https://openalex.org/W6713134421","https://openalex.org/W6740240939","https://openalex.org/W6746031088","https://openalex.org/W6973666849"],"related_works":["https://openalex.org/W2911525106","https://openalex.org/W2736239746","https://openalex.org/W2169083538","https://openalex.org/W2397763568","https://openalex.org/W1945018945","https://openalex.org/W3154661292","https://openalex.org/W3037127226","https://openalex.org/W4367793605","https://openalex.org/W3208111892","https://openalex.org/W3042204386"],"abstract_inverted_index":{"Zero":[0],"resource":[1],"speech":[2,23,89],"recognition":[3,138],"is":[4,27,52,67,74,129,140,162],"getting":[5],"attention":[6],"for":[7,57,106],"engineering":[8],"as":[9,11,122],"well":[10],"scientific":[12],"purposes.":[13],"Based":[14],"on":[15,86,152],"the":[16,65,72,80,119,153,158],"existing":[17],"unsupervised":[18],"learning":[19,134],"frameworks":[20],"using":[21,69,114],"only":[22],"input,":[24],"however,":[25],"it":[26,128],"impossible":[28],"to":[29,54,75],"associate":[30],"automatically":[31],"found":[32],"linguistic":[33],"units":[34],"with":[35],"spellings":[36],"and":[37,99,124,155],"concepts.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,91,131,156],"propose":[43],"an":[44,62],"approach":[45,66],"that":[46,51,133,161],"uses":[47],"a":[48,77,103,135],"scalar":[49],"reward":[50,100],"assumed":[53],"be":[55],"given":[56],"each":[58],"decoding":[59],"result":[60],"of":[61,82,144],"utterance.":[63],"While":[64,127],"straightforward":[68],"reinforcement":[70,109],"learning,":[71],"difficulty":[73],"obtain":[76],"convergence":[78],"without":[79],"help":[81],"supervised":[83,166],"learning.":[84,110],"Focusing":[85],"encoder-decoder":[87],"based":[88],"recognition,":[90],"explore":[92],"several":[93],"neural":[94],"network":[95],"architectures,":[96],"optimization":[97],"methods,":[98],"definitions,":[101],"seeking":[102],"suitable":[104],"configuration":[105],"policy":[107],"gradient":[108],"Experiments":[111],"were":[112],"performed":[113],"connected":[115,136],"digit":[116,137,145],"utterances":[117],"from":[118,165],"TIDIGITS":[120],"corpus":[121],"training":[123],"evaluation":[125],"sets.":[126],"challenging,":[130],"show":[132],"system":[139],"possible":[141],"achieving":[142],"13.6%":[143],"error":[146],"rate.":[147],"The":[148],"success":[149],"largely":[150,163],"depends":[151],"configurations":[154],"reveal":[157],"appropriate":[159],"condition":[160],"different":[164],"training.":[167]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}