{"id":"https://openalex.org/W4205850803","doi":"https://doi.org/10.1109/ialp54817.2021.9675280","title":"Indonesian speech recognition based on Deep Neural Network","display_name":"Indonesian speech recognition based on Deep Neural Network","publication_year":2021,"publication_date":"2021-12-11","ids":{"openalex":"https://openalex.org/W4205850803","doi":"https://doi.org/10.1109/ialp54817.2021.9675280"},"language":"en","primary_location":{"id":"doi:10.1109/ialp54817.2021.9675280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp54817.2021.9675280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5016984773","display_name":"Ruolin Yang","orcid":"https://orcid.org/0000-0001-6241-6317"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruolin Yang","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076764073","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-0488-1514"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041966370","display_name":"Yu Lu","orcid":"https://orcid.org/0000-0002-8647-3014"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Lu","raw_affiliation_strings":["School of Information Science and Engineering, Yunnan University, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"41"},"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":0.9861999750137329,"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/T10860","display_name":"Speech and Audio Processing","score":0.9822999835014343,"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/computer-science","display_name":"Computer science","score":0.8229731321334839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7425608038902283},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6587732434272766},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6464079022407532},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.6401443481445312},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5996506810188293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5723066329956055},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5320461988449097},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5007855892181396},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48803749680519104},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.48250651359558105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4036538600921631},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32816243171691895},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31231409311294556},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06669756770133972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8229731321334839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7425608038902283},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6587732434272766},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6464079022407532},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.6401443481445312},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5996506810188293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5723066329956055},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5320461988449097},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5007855892181396},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48803749680519104},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.48250651359558105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4036538600921631},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32816243171691895},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31231409311294556},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06669756770133972},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp54817.2021.9675280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp54817.2021.9675280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2109389024","https://openalex.org/W2125838338","https://openalex.org/W2160815625","https://openalex.org/W2802023636","https://openalex.org/W2913200330","https://openalex.org/W2982533268","https://openalex.org/W3015457435","https://openalex.org/W3047026237","https://openalex.org/W3079443720","https://openalex.org/W3103064977","https://openalex.org/W3120338682","https://openalex.org/W3126911992","https://openalex.org/W6631362777","https://openalex.org/W7039088390"],"related_works":["https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W151018310","https://openalex.org/W2784059283","https://openalex.org/W4319779560","https://openalex.org/W4367598165","https://openalex.org/W4385611764"],"abstract_inverted_index":{"The":[0,114],"speech":[1,38,44,62,89,150],"recognition":[2,45,90],"system":[3,91],"using":[4],"deep":[5,53,69],"neural":[6,54,70],"network":[7,55,71],"and":[8,32,72,77,94,105,152],"large-scale":[9],"datasets":[10],"have":[11],"had":[12],"good":[13],"performance.":[14],"Indonesian":[15,43,61,88,149],"is":[16,57,101,111,141,157,169],"a":[17],"language":[18],"with":[19,160],"hundreds":[20],"of":[21,23,30,35,42,49,68,87,97,148],"millions":[22],"people.":[24],"Due":[25],"to":[26,59,65,83],"the":[27,33,40,52,66,73,85,95,106,119,131,144,153,161,165],"late":[28],"start":[29],"research":[31,41],"lack":[34],"large":[36],"enough":[37],"data,":[39],"lags.":[46],"In":[47,136],"view":[48],"this":[50,137,139],"situation,":[51],"model":[56,108,121,140,147],"used":[58,142],"study":[60],"recognition.":[63],"According":[64],"transferability":[67],"similarity":[74],"between":[75],"English":[76],"Indonesian,":[78],"three":[79],"transfer":[80,99,126,134],"learning":[81],"methods":[82,100],"improve":[84],"performance":[86,129],"are":[92],"proposed,":[93],"effectiveness":[96],"different":[98],"verified":[102],"by":[103,172],"experiments,":[104],"acoustic":[107,146],"training":[109],"scheme":[110],"further":[112],"optimized.":[113],"experimental":[115],"results":[116],"show":[117],"that":[118],"TDNN-Attention-HMM":[120],"based":[122],"on":[123],"hierarchical":[124],"weight":[125],"has":[127],"better":[128],"than":[130],"other":[132],"two":[133],"models.":[135],"paper,":[138],"as":[143],"optimal":[145],"recognition,":[151],"word":[154,166],"error":[155,167],"rate":[156,168],"6.79%.":[158],"Compared":[159],"DNN-HMM":[162],"baseline":[163],"system,":[164],"relatively":[170],"reduced":[171],"26.52":[173],"%.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}