{"id":"https://openalex.org/W7130380390","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385096","title":"Exploring the Impact of Data Quantity on Asr in Extremely Low-Resource Languages","display_name":"Exploring the Impact of Data Quantity on Asr in Extremely Low-Resource Languages","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7130380390","doi":"https://doi.org/10.1109/o-cocosda68185.2025.11385096"},"language":null,"primary_location":{"id":"doi:10.1109/o-cocosda68185.2025.11385096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th 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":"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/A5002404521","display_name":"Yao-Fei Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao-Fei Cheng","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108832513","display_name":"Liwei Chen","orcid":"https://orcid.org/0000-0003-4160-9771"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Wei Chen","raw_affiliation_strings":["National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126288966","display_name":"Hung-Shin Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136767","display_name":"Link Institut (Switzerland)","ror":"https://ror.org/04vhpaz11","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210136767"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["United Link Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"United Link Co., Ltd","institution_ids":["https://openalex.org/I4210136767"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033417091","display_name":"H. L. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69126097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T13194","display_name":"ICT in Developing Communities","score":0.3596999943256378,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13194","display_name":"ICT in Developing Communities","score":0.3596999943256378,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.25850000977516174,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.04270000010728836,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6554999947547913},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5770999789237976},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5239999890327454},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4925000071525574},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.49070000648498535},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.3889999985694885},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3750999867916107},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.34610000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033999800682068},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5392000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5300999879837036},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4925000071525574},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.49070000648498535},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47620001435279846},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C13460635","wikidata":"https://www.wikidata.org/wiki/Q85753676","display_name":"Classification scheme","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda68185.2025.11385096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda68185.2025.11385096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 28th 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":[{"display_name":"Quality Education","score":0.4589070677757263,"id":"https://metadata.un.org/sdg/4"},{"display_name":"Reduced inequalities","score":0.4030541777610779,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1995443851","https://openalex.org/W2127141656","https://openalex.org/W2132870739","https://openalex.org/W2296719434","https://openalex.org/W2739967986","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2973049979","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3197580070","https://openalex.org/W3198429080","https://openalex.org/W3198771897","https://openalex.org/W3203407300","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4310348293","https://openalex.org/W4319862255","https://openalex.org/W4385572536","https://openalex.org/W4385822693","https://openalex.org/W7126386560"],"related_works":[],"abstract_inverted_index":{"This":[0,65],"study":[1],"investigates":[2],"the":[3,25,36,42,60,87,101,108,115,134],"efficacy":[4],"of":[5,27,38,45,103,117,138],"data":[6,39,106,139],"augmentation":[7,140],"techniques":[8],"for":[9,126,145],"low-resource":[10,32,146],"automatic":[11],"speech":[12],"recognition":[13],"(ASR),":[14],"focusing":[15],"on":[16,41,96],"two":[17],"endangered":[18],"Austronesian":[19],"languages,":[20],"Amis":[21,128],"and":[22,75,83,93,129,136],"Seediq.":[23,130],"Recognizing":[24],"potential":[26],"self-supervised":[28],"learning":[29,144],"(SSL)":[30],"in":[31,107,123],"settings,":[33],"we":[34],"explore":[35],"impact":[37],"volume":[40],"continued":[43],"pre-training":[44],"SSL":[46],"models.":[47],"We":[48],"propose":[49],"a":[50,55,68],"novel":[51],"data-selection":[52],"scheme":[53,66],"leveraging":[54],"multilingual":[56],"corpus":[57],"to":[58,71,79,86],"augment":[59],"limited":[61],"target":[62,88],"language":[63,69,147],"data.":[64],"utilizes":[67],"classifier":[70],"extract":[72],"utterance":[73],"embeddings":[74],"employs":[76],"one-class":[77],"classifiers":[78],"identify":[80],"utterances":[81],"phonetically":[82],"phonologically":[84],"proximate":[85],"languages.":[89],"Utterances":[90],"are":[91],"ranked":[92],"selected":[94],"based":[95],"their":[97],"decision":[98],"scores,":[99],"ensuring":[100],"inclusion":[102],"highly":[104],"relevant":[105],"SSL-ASR":[109],"pipeline.":[110],"Our":[111],"experimental":[112],"results":[113],"demonstrate":[114],"effectiveness":[116],"this":[118],"approach,":[119],"yielding":[120],"substantial":[121],"improvements":[122],"ASR":[124],"performance":[125],"both":[127],"These":[131],"findings":[132],"underscore":[133],"feasibility":[135],"promise":[137],"through":[141],"cross-lingual":[142],"transfer":[143],"ASR.":[148]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2026-02-19T00:00:00"}