{"id":"https://openalex.org/W4405633338","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800336","title":"Enhancing Indonesian Automatic Speech Recognition: Evaluating Multilingual Models with Diverse Speech Variabilities","display_name":"Enhancing Indonesian Automatic Speech Recognition: Evaluating Multilingual Models with Diverse Speech Variabilities","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633338","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800336"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5114331340","display_name":"Aulia Adila","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Aulia Adila","raw_affiliation_strings":["Institut Teknologi Bandung,Indonesia"],"affiliations":[{"raw_affiliation_string":"Institut Teknologi Bandung,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109119353","display_name":"Dessi Puji Lestari","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dessi Lestari","raw_affiliation_strings":["Institut Teknologi Bandung,Indonesia"],"affiliations":[{"raw_affiliation_string":"Institut Teknologi Bandung,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021128017","display_name":"Ayu Purwarianti","orcid":"https://orcid.org/0000-0002-5016-3700"},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ayu Purwarianti","raw_affiliation_strings":["Institut Teknologi Bandung,Indonesia"],"affiliations":[{"raw_affiliation_string":"Institut Teknologi Bandung,Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066930701","display_name":"Dipta Tanaya","orcid":"https://orcid.org/0009-0000-1480-8041"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dipta Tanaya","raw_affiliation_strings":["University of Indonesia,Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066073372","display_name":"Kurniawati Azizah","orcid":"https://orcid.org/0000-0002-3217-7025"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Kurniawati Azizah","raw_affiliation_strings":["University of Indonesia,Indonesia"],"affiliations":[{"raw_affiliation_string":"University of Indonesia,Indonesia","institution_ids":["https://openalex.org/I29617571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114331340"],"corresponding_institution_ids":["https://openalex.org/I134635517"],"apc_list":null,"apc_paid":null,"fwci":1.0911,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82639025,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922999739646912,"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":0.9922999739646912,"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":0.925599992275238,"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":0.916700005531311,"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":0.7831759452819824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7321608066558838},{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.7113730907440186},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5451298952102661},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4787237346172333},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4292076528072357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3820333778858185},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3161267638206482},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17896848917007446}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831759452819824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7321608066558838},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.7113730907440186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5451298952102661},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4787237346172333},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4292076528072357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3820333778858185},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3161267638206482},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17896848917007446},{"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/o-cocosda64382.2024.10800336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800336","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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":15,"referenced_works":["https://openalex.org/W22876683","https://openalex.org/W1986993325","https://openalex.org/W1999860150","https://openalex.org/W2127141656","https://openalex.org/W2134630765","https://openalex.org/W2963303951","https://openalex.org/W4256161595","https://openalex.org/W4315645596","https://openalex.org/W4319862635","https://openalex.org/W4391021683","https://openalex.org/W4392355216","https://openalex.org/W6679855610","https://openalex.org/W6728823536","https://openalex.org/W6771467084","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W4253660971","https://openalex.org/W2041273198","https://openalex.org/W1599055764"],"abstract_inverted_index":{"An":[0],"ideal":[1],"speech":[2,10,16,25,50,72,78,87,105,122],"recognition":[3,79,88],"model":[4,40,137,166],"has":[5],"the":[6,115,134,146,168],"capability":[7],"to":[8,64,108,119],"transcribe":[9,120],"accurately":[11],"under":[12],"various":[13,141],"characteristics":[14],"of":[15,45,67],"signals,":[17],"such":[18,38],"as":[19,97,99,143],"speaking":[20,162],"style":[21,163],"(read":[22],"and":[23,28,30,35,60,95,153],"spontaneous),":[24],"context":[26],"(formal":[27],"informal),":[29],"background":[31],"noise":[32],"conditions":[33],"(clean":[34],"moderate).":[36],"Building":[37],"a":[39,42,65,101],"requires":[41],"significant":[43],"amount":[44],"training":[46],"data":[47,54,69,123],"with":[48,70,106,140],"diverse":[49],"characteristics.":[51],"Currently,":[52],"Indonesian":[53,68,76,104,121],"is":[55],"dominated":[56],"by":[57,133,145],"read,":[58],"formal,":[59],"clean":[61],"speech,":[62],"leading":[63],"scarcity":[66],"other":[71],"variabilities.":[73],"To":[74],"develop":[75],"automatic":[77],"(ASR),":[80],"we":[81,159],"present":[82],"our":[83,110],"research":[84],"on":[85],"state-of-the-art":[86],"models,":[89],"namely":[90],"Massively":[91],"Multilingual":[92],"Speech":[93],"(MMS)":[94],"Whisper,":[96],"well":[98],"compiling":[100],"dataset":[102],"comprising":[103],"variabilities":[107],"facilitate":[109],"study.":[111],"We":[112],"further":[113],"investigate":[114],"models'":[116],"predictive":[117],"ability":[118],"across":[124,138],"different":[125],"variability":[126,164],"groups.":[127],"The":[128],"best":[129],"results":[130],"were":[131],"achieved":[132],"Whisper":[135],"fine-tuned":[136],"datasets":[139],"characteristics,":[142],"indicated":[144],"decrease":[147],"in":[148],"word":[149],"error":[150,155],"rate":[151,156],"(WER)":[152],"character":[154],"(CER).":[157],"Moreover,":[158],"found":[160],"that":[161],"affected":[165],"performance":[167],"most.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}