{"id":"https://openalex.org/W3161704976","doi":"https://doi.org/10.1109/access.2021.3077441","title":"Improved Transcription and Speaker Identification System for Concurrent Speech in Bahasa Indonesia Using Recurrent Neural Network","display_name":"Improved Transcription and Speaker Identification System for Concurrent Speech in Bahasa Indonesia Using Recurrent Neural Network","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3161704976","doi":"https://doi.org/10.1109/access.2021.3077441","mag":"3161704976"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3077441","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3077441","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2021.3077441","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079265931","display_name":"Muhammad Bagus Andra","orcid":"https://orcid.org/0000-0002-7909-5887"},"institutions":[{"id":"https://openalex.org/I168595927","display_name":"Kumamoto Health Science University","ror":"https://ror.org/03pm2yz25","country_code":"JP","type":"education","lineage":["https://openalex.org/I168595927"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Muhammad Bagus Andra","raw_affiliation_strings":["Department of Computer Science and Electrical Engineering, Kumamoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7909-5887","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Electrical Engineering, Kumamoto, Japan","institution_ids":["https://openalex.org/I168595927"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027000175","display_name":"Tsuyoshi Usagawa","orcid":"https://orcid.org/0000-0002-0746-0072"},"institutions":[{"id":"https://openalex.org/I168595927","display_name":"Kumamoto Health Science University","ror":"https://ror.org/03pm2yz25","country_code":"JP","type":"education","lineage":["https://openalex.org/I168595927"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuyoshi Usagawa","raw_affiliation_strings":["Department of Computer Science and Electrical Engineering, Kumamoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Electrical Engineering, Kumamoto, Japan","institution_ids":["https://openalex.org/I168595927"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.4198,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68400207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"9","issue":null,"first_page":"70758","last_page":"70774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","score":0.9825000166893005,"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":0.8380095362663269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6818022727966309},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.588477611541748},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5870188474655151},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5732022523880005},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5719045996665955},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5499659180641174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4323922395706177},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.41966211795806885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33174484968185425}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8380095362663269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6818022727966309},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.588477611541748},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5870188474655151},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5732022523880005},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5719045996665955},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5499659180641174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4323922395706177},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.41966211795806885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33174484968185425},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3077441","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3077441","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bfb08395e2044a26aad2ff250b1e5c75","is_oa":true,"landing_page_url":"https://doaj.org/article/bfb08395e2044a26aad2ff250b1e5c75","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 70758-70774 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3077441","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3077441","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G3108483373","display_name":null,"funder_award_id":"19H1225100","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"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":57,"referenced_works":["https://openalex.org/W6558424","https://openalex.org/W22876683","https://openalex.org/W57926798","https://openalex.org/W84501689","https://openalex.org/W148837159","https://openalex.org/W382290953","https://openalex.org/W1494198834","https://openalex.org/W1532011044","https://openalex.org/W1968939597","https://openalex.org/W2023217006","https://openalex.org/W2055276857","https://openalex.org/W2097085462","https://openalex.org/W2109389024","https://openalex.org/W2118945896","https://openalex.org/W2138660131","https://openalex.org/W2140828385","https://openalex.org/W2166637769","https://openalex.org/W2193413348","https://openalex.org/W2221409856","https://openalex.org/W2250274411","https://openalex.org/W2327501763","https://openalex.org/W2460742184","https://openalex.org/W2483158495","https://openalex.org/W2547039119","https://openalex.org/W2552071709","https://openalex.org/W2601477764","https://openalex.org/W2611419415","https://openalex.org/W2785470264","https://openalex.org/W2890111732","https://openalex.org/W2906459023","https://openalex.org/W2913425402","https://openalex.org/W2916997151","https://openalex.org/W2936423518","https://openalex.org/W2950224550","https://openalex.org/W2953278544","https://openalex.org/W2962824709","https://openalex.org/W2966594098","https://openalex.org/W2971275122","https://openalex.org/W2972988966","https://openalex.org/W2973481893","https://openalex.org/W2990384275","https://openalex.org/W2995929068","https://openalex.org/W2996302186","https://openalex.org/W2998830286","https://openalex.org/W3030437843","https://openalex.org/W3038809454","https://openalex.org/W3085006933","https://openalex.org/W3097932604","https://openalex.org/W3127686677","https://openalex.org/W6603446691","https://openalex.org/W6606109230","https://openalex.org/W6680587008","https://openalex.org/W6687566353","https://openalex.org/W6691387866","https://openalex.org/W6728823536","https://openalex.org/W6764115395","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W200981350","https://openalex.org/W4386907265","https://openalex.org/W2944691285","https://openalex.org/W2058752985","https://openalex.org/W2293740626","https://openalex.org/W1499712254","https://openalex.org/W2915347927"],"abstract_inverted_index":{"Bahasa":[0,36],"Indonesia":[1],"is":[2,41,78,86],"one":[3],"of":[4,113,121,167],"the":[5,67,82,139,146,151,157],"most":[6],"prominent":[7],"low-resource":[8],"Languages":[9],"that":[10,138],"still":[11],"lack":[12],"development":[13],"in":[14,35,43,69,150,156],"regards":[15],"to":[16,65,80,103,106,127,145],"communication-assisting":[17],"technology.":[18],"This":[19],"paper":[20],"proposes":[21],"an":[22,48,90,161],"improved":[23,88],"system":[24,55,100],"for":[25,119,169,173,178],"generating":[26],"transcript":[27,84,118],"and":[28,51,94,115,154,176],"identifying":[29],"speakers":[30,68,108],"from":[31],"a":[32,44,70,110,117],"concurrent":[33,71],"speech":[34,63],"Indonesia.":[37],"The":[38,54,98,135],"proposed":[39,99,140],"method":[40,141],"applicable":[42],"situation":[45],"such":[46],"as":[47],"online":[49],"meeting":[50],"remote":[52],"conference.":[53],"combines":[56],"Reinforced":[57],"Learning":[58],"(RL)":[59],"Model":[60],"with":[61,109,123,132,160],"pitch-aware":[62],"separation":[64],"identify":[66,104],"speech.":[72],"A":[73],"Recurrent":[74],"Neural":[75],"Network":[76],"(RNN)":[77],"utilized":[79],"generate":[81,116],"text":[83],"which":[85],"later":[87],"by":[89],"external":[91],"language":[92],"model":[93],"spelling":[95],"correction":[96],"model.":[97],"was":[101],"able":[102],"up":[105],"5":[107],"variable":[111],"degree":[112],"confidence":[114],"each":[120],"them":[122],"better":[124,143],"quality":[125],"compared":[126,144],"other":[128],"methods":[129],"when":[130],"evaluated":[131],"several":[133],"metrics.":[134],"result":[136],"shows":[137],"perform":[142],"baseline":[147],"method,":[148],"even":[149],"single-speaker":[152],"situation,":[153,159],"function":[155],"simultaneous-speech":[158],"average":[162],"Word":[163],"Error":[164],"Rate":[165],"(WER)":[166],"16.59%":[168],"two":[170],"speakers,":[171,175],"26.72%":[172],"three":[174],"31.50%":[177],"four":[179],"speakers.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}