{"id":"https://openalex.org/W3200887081","doi":"https://doi.org/10.1109/asru51503.2021.9688301","title":"Leveraging Pre-Trained Representations to Improve Access to Untranscribed Speech from Endangered Languages","display_name":"Leveraging Pre-Trained Representations to Improve Access to Untranscribed Speech from Endangered Languages","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3200887081","doi":"https://doi.org/10.1109/asru51503.2021.9688301","mag":"3200887081"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688301","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11370/44dff201-59a8-41ab-8626-5bd4601d6d67","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012458624","display_name":"Nay San","orcid":"https://orcid.org/0000-0002-3533-5025"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["AU","US"],"is_corresponding":true,"raw_author_name":"Nay San","raw_affiliation_strings":["Stanford University,Department of Linguistics","College of Arts and Social Sciences, Australian National University","ARC Centre of Excellence for the Dynamics of Language"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Linguistics","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"College of Arts and Social Sciences, Australian National University","institution_ids":["https://openalex.org/I118347636"]},{"raw_affiliation_string":"ARC Centre of Excellence for the Dynamics of Language","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033914946","display_name":"Martijn Bartelds","orcid":"https://orcid.org/0000-0003-1006-8669"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Martijn Bartelds","raw_affiliation_strings":["University of Groningen,Department of Computational Linguistics"],"affiliations":[{"raw_affiliation_string":"University of Groningen,Department of Computational Linguistics","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088740812","display_name":"Mitchell Browne","orcid":"https://orcid.org/0000-0001-7623-8179"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mitchell Browne","raw_affiliation_strings":["ARC Centre of Excellence for the Dynamics of Language","School of Languages and Cultures, University of Queensland"],"affiliations":[{"raw_affiliation_string":"ARC Centre of Excellence for the Dynamics of Language","institution_ids":[]},{"raw_affiliation_string":"School of Languages and Cultures, University of Queensland","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082863197","display_name":"Lily Clifford","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lily Clifford","raw_affiliation_strings":["Stanford University,Department of Linguistics"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Linguistics","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034028267","display_name":"Fiona Gibson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fiona Gibson","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064414060","display_name":"John Mansfield","orcid":"https://orcid.org/0000-0003-1167-1136"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"John Mansfield","raw_affiliation_strings":["ARC Centre of Excellence for the Dynamics of Language","School of Languages and Linguistics, University of Melbourne"],"affiliations":[{"raw_affiliation_string":"ARC Centre of Excellence for the Dynamics of Language","institution_ids":[]},{"raw_affiliation_string":"School of Languages and Linguistics, University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013702307","display_name":"David T. Nash","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Nash","raw_affiliation_strings":["ARC Centre of Excellence for the Dynamics of Language","College of Arts and Social Sciences, Australian National University"],"affiliations":[{"raw_affiliation_string":"ARC Centre of Excellence for the Dynamics of Language","institution_ids":[]},{"raw_affiliation_string":"College of Arts and Social Sciences, Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027313930","display_name":"Jane Simpson","orcid":"https://orcid.org/0000-0002-7487-1234"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jane Simpson","raw_affiliation_strings":["ARC Centre of Excellence for the Dynamics of Language","College of Arts and Social Sciences, Australian National University"],"affiliations":[{"raw_affiliation_string":"ARC Centre of Excellence for the Dynamics of Language","institution_ids":[]},{"raw_affiliation_string":"College of Arts and Social Sciences, Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012693173","display_name":"Myfany Turpin","orcid":"https://orcid.org/0000-0003-0395-6756"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Myfany Turpin","raw_affiliation_strings":["ARC Centre of Excellence for the Dynamics of Language","Sydney Conservatorium of Music, University of Sydney"],"affiliations":[{"raw_affiliation_string":"ARC Centre of Excellence for the Dynamics of Language","institution_ids":[]},{"raw_affiliation_string":"Sydney Conservatorium of Music, University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081830016","display_name":"Maria Vollmer","orcid":"https://orcid.org/0000-0003-2424-159X"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["AU","DE"],"is_corresponding":false,"raw_author_name":"Maria Vollmer","raw_affiliation_strings":["ARC Centre of Excellence for the Dynamics of Language","University of Freiburg","College of Arts and Social Sciences, Australian National University"],"affiliations":[{"raw_affiliation_string":"ARC Centre of Excellence for the Dynamics of Language","institution_ids":[]},{"raw_affiliation_string":"University of Freiburg","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"College of Arts and Social Sciences, Australian National University","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068304444","display_name":"Sasha Wilmoth","orcid":"https://orcid.org/0000-0002-6626-9104"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sasha Wilmoth","raw_affiliation_strings":["ARC Centre of Excellence for the Dynamics of Language","School of Languages and Linguistics, University of Melbourne"],"affiliations":[{"raw_affiliation_string":"ARC Centre of Excellence for the Dynamics of Language","institution_ids":[]},{"raw_affiliation_string":"School of Languages and Linguistics, University of Melbourne","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087088138","display_name":"Dan Jurafsky","orcid":"https://orcid.org/0000-0002-6459-7745"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Jurafsky","raw_affiliation_strings":["Stanford University,Department of Linguistics"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Linguistics","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5012458624"],"corresponding_institution_ids":["https://openalex.org/I118347636","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.0151,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79918677,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1094","last_page":"1101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9944000244140625,"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":0.8463021516799927},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6928418874740601},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6165916323661804},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5490789413452148},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5096399784088135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46970388293266296},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4110693335533142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8463021516799927},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6928418874740601},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6165916323661804},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5490789413452148},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5096399784088135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46970388293266296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4110693335533142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru51503.2021.9688301","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688301","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/44dff201-59a8-41ab-8626-5bd4601d6d67","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/44dff201-59a8-41ab-8626-5bd4601d6d67","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"San, N, Bartelds, M, Browne, M, Clifford, L, Gibson, F, Mansfield, J, Nash, D, Simpson, J, Turpin, M, Vollmer, M, Wilmoth, S & Jurafsky, D 2022 'Leveraging pre-trained representations to improve access to untranscribed speech from endangered languages' IEEE. https://doi.org/10.1109/ASRU51503.2021.9688301","raw_type":"info:eu-repo/semantics/workingPaper"},{"id":"pmh:rug:oai:pure.rug.nl:publications/44dff201-59a8-41ab-8626-5bd4601d6d67","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/44dff201-59a8-41ab-8626-5bd4601d6d67","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/workingpaper"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/44dff201-59a8-41ab-8626-5bd4601d6d67","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/44dff201-59a8-41ab-8626-5bd4601d6d67","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"San, N, Bartelds, M, Browne, M, Clifford, L, Gibson, F, Mansfield, J, Nash, D, Simpson, J, Turpin, M, Vollmer, M, Wilmoth, S & Jurafsky, D 2022 'Leveraging pre-trained representations to improve access to untranscribed speech from endangered languages' IEEE. https://doi.org/10.1109/ASRU51503.2021.9688301","raw_type":"info:eu-repo/semantics/workingPaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6299999952316284,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1594560709","https://openalex.org/W2076307659","https://openalex.org/W2088615611","https://openalex.org/W2137044559","https://openalex.org/W2294799344","https://openalex.org/W2442329935","https://openalex.org/W2805607737","https://openalex.org/W2888951652","https://openalex.org/W2899377381","https://openalex.org/W2946417913","https://openalex.org/W2957905185","https://openalex.org/W2972764223","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2996383576","https://openalex.org/W3015522062","https://openalex.org/W3019546258","https://openalex.org/W3036601975","https://openalex.org/W3037057938","https://openalex.org/W3099782249","https://openalex.org/W3107720207","https://openalex.org/W3117408830","https://openalex.org/W3174056976","https://openalex.org/W3198429080","https://openalex.org/W4211190719","https://openalex.org/W4239270640","https://openalex.org/W6718561954","https://openalex.org/W6756326128","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6786071721","https://openalex.org/W6794685259"],"related_works":["https://openalex.org/W3024364549","https://openalex.org/W2032233321","https://openalex.org/W4206019083","https://openalex.org/W1976265003","https://openalex.org/W2054476758","https://openalex.org/W2370378377","https://openalex.org/W2048865712","https://openalex.org/W3121970507","https://openalex.org/W4210535024","https://openalex.org/W4237510188"],"abstract_inverted_index":{"Pre-trained":[0],"speech":[1,12,50,121],"representations":[2,86,122,131],"like":[3],"wav2vec":[4,129],"2.0":[5,130],"are":[6,27,73],"a":[7,32,65],"powerful":[8],"tool":[9],"for":[10,22,46,88,123],"automatic":[11],"recognition":[13],"(ASR).":[14],"Yet":[15],"many":[16],"endangered":[17,74,146],"languages":[18,63],"lack":[19],"sufficient":[20],"data":[21,58],"pre-training":[23],"such":[24],"models,":[25],"or":[26,75,134],"predominantly":[28],"oral":[29],"vernaculars":[30],"without":[31],"standardised":[33],"writing":[34],"system,":[35],"precluding":[36],"fine-tuning.":[37],"Query-by-example":[38],"spoken":[39,54],"term":[40],"detection":[41],"(QbE-STD)":[42],"offers":[43],"an":[44],"alternative":[45],"iteratively":[47],"indexing":[48],"untranscribed":[49],"corpora":[51],"by":[52,84],"locating":[53],"query":[55],"terms.":[56],"Using":[57],"from":[59],"7":[60],"Australian":[61,110],"Aboriginal":[62],"and":[64,96],"regional":[66],"variety":[67],"of":[68,71],"Dutch,":[69],"all":[70],"which":[72],"vulnerable,":[76],"we":[77,126],"show":[78],"that":[79,128],"QbE-STD":[80],"can":[81],"be":[82],"improved":[83],"leveraging":[85],"developed":[87],"ASR":[89],"(wav2vec":[90],"2.0:":[91],"the":[92,101,105],"English":[93,102,133],"monolingual":[94],"model":[95,103,107],"XLSR53":[97],"multilingual":[98,106],"model).":[99],"Surprisingly,":[100],"outperformed":[104],"on":[108,144],"4":[109],"language":[111,147],"datasets,":[112],"raising":[113],"questions":[114],"around":[115],"how":[116],"to":[117],"optimally":[118],"leverage":[119],"self-supervised":[120],"QbE-STD.":[124],"Nevertheless,":[125],"find":[127],"(either":[132],"XLSR53)":[135],"offer":[136],"large":[137],"improvements":[138],"(56-86%":[139],"relative)":[140],"over":[141],"state-of-the-art":[142],"approaches":[143],"our":[145],"datasets.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}