{"id":"https://openalex.org/W4391021639","doi":"https://doi.org/10.1109/asru57964.2023.10389734","title":"Evaluating Self-Supervised Speech Models on a Taiwanese Hokkien Corpus","display_name":"Evaluating Self-Supervised Speech Models on a Taiwanese Hokkien Corpus","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021639","doi":"https://doi.org/10.1109/asru57964.2023.10389734"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389734","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5019548123","display_name":"Yi-Hui Chou","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi-Hui Chou","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027404450","display_name":"Kalvin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kalvin Chang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111704849","display_name":"Meng-Ju Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng-Ju Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016784678","display_name":"Winston Ou","orcid":null},"institutions":[{"id":"https://openalex.org/I16970960","display_name":"Scripps College","ror":"https://ror.org/00p55jd14","country_code":"US","type":"education","lineage":["https://openalex.org/I16970960"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Winston Ou","raw_affiliation_strings":["Scripps College","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scripps College","institution_ids":["https://openalex.org/I16970960"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093487558","display_name":"Alice Wen-Hsin Bi","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alice Wen-Hsin Bi","raw_affiliation_strings":["University of Maryland","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076487842","display_name":"Carol Yang","orcid":"https://orcid.org/0000-0002-5760-3262"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carol Yang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081706247","display_name":"Bryan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I118020396","display_name":"Swarthmore College","ror":"https://ror.org/012dg8a96","country_code":"US","type":"education","lineage":["https://openalex.org/I118020396"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bryan Y. Chen","raw_affiliation_strings":["Swarthmore College","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swarthmore College","institution_ids":["https://openalex.org/I118020396"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073623379","display_name":"Rong-Wei Pai","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Rong-Wei Pai","raw_affiliation_strings":["National Taiwan Normal University","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University","institution_ids":["https://openalex.org/I134161618"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114041130","display_name":"Po-Yen Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I184693016","display_name":"China Medical University","ror":"https://ror.org/00v408z34","country_code":"TW","type":"education","lineage":["https://openalex.org/I184693016"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Po-Yen Yeh","raw_affiliation_strings":["China Medical University,Taiwan","China Medical University, Taiwan","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Medical University,Taiwan","institution_ids":["https://openalex.org/I184693016"]},{"raw_affiliation_string":"China Medical University, Taiwan","institution_ids":["https://openalex.org/I184693016"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105843310","display_name":"Jo-Peng Chiang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Jo-Peng Chiang","raw_affiliation_strings":["National Taiwan University","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093745516","display_name":"Iu-Tshiann Phoann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iu-Tshiann Phoann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102606574","display_name":"Winnie Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Winnie Chang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074099926","display_name":"Chenxuan Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenxuan Cui","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069058013","display_name":"Noel Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Noel Chen","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101063912","display_name":"Jiatong Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5019548123"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.1647,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59612577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9987000226974487,"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":0.698979377746582},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6266530752182007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5532228946685791},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.418615460395813},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3576994240283966},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05638626217842102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698979377746582},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6266530752182007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5532228946685791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.418615460395813},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3576994240283966},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05638626217842102}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389734","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6600000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W402997520","https://openalex.org/W809880175","https://openalex.org/W1246859950","https://openalex.org/W1522301498","https://openalex.org/W1564346437","https://openalex.org/W2016617539","https://openalex.org/W2101105183","https://openalex.org/W2486052362","https://openalex.org/W2912887861","https://openalex.org/W2914304175","https://openalex.org/W2933138175","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W3105214104","https://openalex.org/W3180374548","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W3213726885","https://openalex.org/W4287854499","https://openalex.org/W4313225456","https://openalex.org/W4385571229","https://openalex.org/W4385573620","https://openalex.org/W4385822439","https://openalex.org/W6631190155","https://openalex.org/W6771467084","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6796464841","https://openalex.org/W6846681180"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Taiwanese":[0,47,56],"Hokkien":[1,48,57],"is":[2,18,22],"declining":[3],"in":[4,15,27,41],"use":[5],"and":[6,29,98],"status":[7],"due":[8],"to":[9,58],"a":[10,23,52,103],"language":[11,26,101],"shift":[12],"towards":[13],"Mandarin":[14],"Taiwan.":[16],"This":[17],"partly":[19],"why":[20],"it":[21],"low":[24],"resource":[25],"NLP":[28],"speech":[30,42,69],"research":[31],"today.":[32],"To":[33],"ensure":[34],"that":[35,76],"the":[36,39,99],"state":[37],"of":[38,55,65],"art":[40],"processing":[43],"does":[44,79],"not":[45,80],"leave":[46],"behind,":[49],"we":[50,74],"contribute":[51],"1.5-hour":[53],"dataset":[54],"MLSUPERB\u2019s":[59],"hidden":[60],"set.":[61],"Evaluating":[62],"ML-SUPERB\u2019s":[63],"suite":[64],"self-supervised":[66],"learning":[67],"(SSL)":[68],"representations":[70],"on":[71],"our":[72],"dataset,":[73],"find":[75],"model":[77],"size":[78],"consistently":[81],"determine":[82],"performance.":[83],"In":[84],"fact,":[85],"certain":[86],"smaller":[87],"models":[88],"outperform":[89],"larger":[90],"ones.":[91],"Furthermore,":[92],"linguistic":[93],"alignment":[94],"between":[95],"pretraining":[96],"data":[97],"target":[100],"plays":[102],"crucial":[104],"role.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-31T08:46:17.908082","created_date":"2025-10-10T00:00:00"}
