{"id":"https://openalex.org/W4401246927","doi":"https://doi.org/10.1109/access.2024.3437755","title":"Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition","display_name":"Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401246927","doi":"https://doi.org/10.1109/access.2024.3437755"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3437755","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3437755","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":null,"license_id":null,"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":"http://dx.doi.org/10.1109/access.2024.3437755","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049205300","display_name":"I-Ting Hsieh","orcid":"https://orcid.org/0009-0001-4446-7476"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"I-Ting Hsieh","raw_affiliation_strings":["Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University, Tainan, Taiwan","Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012935183","display_name":"Zhe-Hong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zhe-Hong Zhao","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049205300"],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65257937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"12","issue":null,"first_page":"106070","last_page":"106083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9979000091552734,"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":0.996399998664856,"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":0.8621116876602173},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7497854232788086},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7294934391975403},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6760416030883789},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6667277812957764},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6532031297683716},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5742853879928589},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5390682816505432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5382954478263855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5344340801239014},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.49173811078071594},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4458085000514984},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41365569829940796},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2768039405345917},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09243640303611755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8621116876602173},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7497854232788086},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7294934391975403},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6760416030883789},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6667277812957764},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6532031297683716},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5742853879928589},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5390682816505432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5382954478263855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5344340801239014},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.49173811078071594},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4458085000514984},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41365569829940796},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2768039405345917},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09243640303611755},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3437755","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3437755","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bc6ad461d10643fc833ec35e08031e90","is_oa":true,"landing_page_url":"https://doaj.org/article/bc6ad461d10643fc833ec35e08031e90","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 106070-106083 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3437755","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3437755","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5411772072","display_name":null,"funder_award_id":"111-2221-E-006-150-MY3","funder_id":"https://openalex.org/F4320331164","funder_display_name":"National Science and Technology Council"}],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W173856587","https://openalex.org/W1494198834","https://openalex.org/W1631260214","https://openalex.org/W2091746061","https://openalex.org/W2127141656","https://openalex.org/W2161742217","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2514741789","https://openalex.org/W2765486990","https://openalex.org/W2936774411","https://openalex.org/W2972818416","https://openalex.org/W2992384298","https://openalex.org/W3007328579","https://openalex.org/W3010079431","https://openalex.org/W3015585292","https://openalex.org/W3035268246","https://openalex.org/W3097777922","https://openalex.org/W3117789470","https://openalex.org/W3118855211","https://openalex.org/W3134043075","https://openalex.org/W3163211337","https://openalex.org/W3174805484","https://openalex.org/W3181014746","https://openalex.org/W3196679449","https://openalex.org/W3207659901","https://openalex.org/W4226017838","https://openalex.org/W4289258965","https://openalex.org/W4294646197","https://openalex.org/W4312120825","https://openalex.org/W4366083739","https://openalex.org/W4384498728","https://openalex.org/W4391592452","https://openalex.org/W4393973323","https://openalex.org/W4399418904","https://openalex.org/W6608710415","https://openalex.org/W6631362777","https://openalex.org/W6736057607","https://openalex.org/W6745289305","https://openalex.org/W6750254146","https://openalex.org/W6791250781","https://openalex.org/W6796027575","https://openalex.org/W6798414287","https://openalex.org/W6798420859","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W156219719","https://openalex.org/W2068412075","https://openalex.org/W2061937230","https://openalex.org/W2132658536","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2784059283","https://openalex.org/W2291624303"],"abstract_inverted_index":{"Under-resourced":[0],"automatic":[1],"speech":[2,44,116,147],"recognition":[3,148],"(ASR)":[4],"has":[5,13],"become":[6],"an":[7],"active":[8],"field":[9],"of":[10,24,83,118,157,185,192],"research":[11],"and":[12,92,114,126,146,187,205,212],"experienced":[14],"significant":[15],"progress":[16],"during":[17],"the":[18,22,50,54,66,84,111,115,151,155,170,201,209],"past":[19],"decade.":[20],"However,":[21],"performance":[23],"under-resourced":[25,55,112],"ASR":[26,37],"trained":[27],"by":[28],"existing":[29],"methods":[30],"is":[31,108],"still":[32],"far":[33],"inferior":[34],"to":[35,89,100,153,161],"high-resourced":[36],"for":[38,62,95,134,165,177,194],"practical":[39],"applications.":[40],"In":[41,104],"this":[42,75,105],"paper,":[43],"data":[45,133],"from":[46,173],"languages":[47],"that":[48],"share":[49],"most":[51],"phonemes":[52],"with":[53,169],"language":[56,73,160,176],"are":[57,128],"selected":[58,109,171],"as":[59,110,130,150],"supplementary":[60,72,131,159,175],"resources":[61],"meta-training":[63,102],"based":[64],"on":[65],"Model-Agnostic":[67],"Meta-Learning":[68],"(MAML)":[69],"strategy.":[70],"Besides":[71],"selection,":[74],"paper":[76],"proposes":[77],"a":[78,181,188],"dynamic":[79,140],"sampling":[80,87,141],"method":[81,88],"instead":[82],"original":[85],"random":[86],"select":[90,162],"support":[91],"query":[93],"sets":[94],"each":[96,158,174],"task":[97],"in":[98],"MAML":[99],"improve":[101],"performance.":[103],"study,":[106],"Taiwanese":[107,195,210],"language,":[113],"corpus":[117,211],"five":[119],"languages,":[120],"including":[121],"Mandarin,":[122],"English,":[123],"Japanese,":[124],"Cantonese,":[125],"Thai,":[127],"chosen":[129],"training":[132],"acoustic":[135],"model":[136,203],"training.":[137],"The":[138],"proposed":[139],"approach":[142],"uses":[143],"phonemes,":[144],"pronunciation,":[145],"models":[149],"basis":[152],"determine":[154],"proportion":[156],"helpful":[163],"utterances":[164,172],"MAML.":[166],"For":[167],"evaluation,":[168],"meta-training,":[178],"we":[179],"obtained":[180],"Word":[182],"Error":[183,190],"Rate":[184,191],"20.24%":[186],"Syllable":[189],"8.35%":[193],"ASR,":[196],"which":[197],"were":[198],"better":[199],"than":[200],"baseline":[202],"(26.18%":[204],"13.99%)":[206],"using":[207],"only":[208],"other":[213],"methods.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}