{"id":"https://openalex.org/W2963144852","doi":"https://doi.org/10.1109/icassp.2018.8461705","title":"Sequence-to-Sequence Asr Optimization Via Reinforcement Learning","display_name":"Sequence-to-Sequence Asr Optimization Via Reinforcement Learning","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2963144852","doi":"https://doi.org/10.1109/icassp.2018.8461705","mag":"2963144852"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461705","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/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"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":true,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"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":"Sakriani Sakti","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"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":"Satoshi Nakamura","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038296765"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":1.7039,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88700979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5829","last_page":"5833"},"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/T10320","display_name":"Neural Networks and Applications","score":0.9951000213623047,"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":0.8019992709159851},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6885806918144226},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5984700918197632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5756919384002686},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.559196949005127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4795662760734558},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45044389367103577},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.42679280042648315},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32040172815322876},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09616473317146301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019992709159851},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6885806918144226},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5984700918197632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5756919384002686},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.559196949005127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4795662760734558},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45044389367103577},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.42679280042648315},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32040172815322876},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09616473317146301},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461705","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1515851193","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1710082047","https://openalex.org/W1895577753","https://openalex.org/W1921523184","https://openalex.org/W1977655452","https://openalex.org/W2016589492","https://openalex.org/W2024490156","https://openalex.org/W2108682071","https://openalex.org/W2109886035","https://openalex.org/W2119717200","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2144499799","https://openalex.org/W2145339207","https://openalex.org/W2163068732","https://openalex.org/W2176263492","https://openalex.org/W2257979135","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2760599032","https://openalex.org/W2952264928","https://openalex.org/W2962759037","https://openalex.org/W2962765220","https://openalex.org/W2962826786","https://openalex.org/W2963167310","https://openalex.org/W2963463964","https://openalex.org/W2965916140","https://openalex.org/W6677929280","https://openalex.org/W6687550071"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W4385893898","https://openalex.org/W2383836440","https://openalex.org/W2610662399","https://openalex.org/W4285757703","https://openalex.org/W2509341624","https://openalex.org/W112480583","https://openalex.org/W2057468170","https://openalex.org/W4221155853"],"abstract_inverted_index":{"Despite":[0],"the":[1,12,22,25,31,34,40,43,47,53,58,67,76,94,100,129,136,148,156,161,165,172,179,188],"success":[2],"of":[3,42,49,57,102,106,131],"sequence-to-sequence":[4,32,124],"approaches":[5],"in":[6,164],"automatic":[7],"speech":[8,50,71],"recognition":[9,114],"(ASR)":[10],"systems,":[11],"models":[13,126],"still":[14],"suffer":[15],"from":[16,79],"several":[17],"problems,":[18],"mainly":[19],"due":[20],"to":[21,38,98,191],"mismatch":[23],"between":[24],"training":[26,103,123,138,166],"and":[27,52,87,168],"inference":[28],"conditions.":[29],"In":[30],"architecture,":[33],"model":[35,68,95,173,193],"is":[36,85,96],"trained":[37,194],"predict":[39],"grapheme":[41,55],"current":[44],"time-step":[45],"given":[46],"input":[48],"signal":[51],"ground-truth":[54],"history":[56],"previous":[59,83],"time-steps.":[60],"However,":[61],"it":[62],"remains":[63],"unclear":[64],"how":[65],"well":[66],"approximates":[69],"real-world":[70],"during":[72],"inference.":[73],"Thus,":[74],"generating":[75],"whole":[77,157],"transcription":[78,158],"scratch":[80],"based":[81,159],"on":[82,160],"predictions":[84],"complicated":[86],"errors":[88],"can":[89,153],"propagate":[90],"over":[91],"time.":[92],"Furthermore,":[93],"optimized":[97],"maximize":[99],"likelihood":[101,142,198],"data":[104],"instead":[105],"error":[107],"rate":[108],"evaluation":[109],"metrics":[110],"that":[111,184],"actually":[112],"quantify":[113],"quality.":[115],"This":[116],"paper":[117],"presents":[118],"an":[119],"alternative":[120],"strategy":[121],"for":[122],"ASR":[125],"by":[127],"adopting":[128],"idea":[130],"reinforcement":[132],"learning":[133],"(RL).":[134],"Unlike":[135],"standard":[137],"scheme":[139],"with":[140,174,196],"maximum":[141,197],"estimation,":[143],"our":[144],"proposed":[145],"approach":[146],"utilizes":[147],"policy":[149],"gradient":[150],"algorithm.":[151],"We":[152],"(1)":[154],"sample":[155],"model's":[162],"prediction":[163],"process":[167],"(2)":[169],"directly":[170],"optimize":[171],"negative":[175],"Levenshtein":[176],"distance":[177],"as":[178],"reward.":[180],"Experimental":[181],"results":[182],"demonstrate":[183],"we":[185],"significantly":[186],"improved":[187],"performance":[189],"compared":[190],"a":[192],"onlv":[195],"estimation.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}