{"id":"https://openalex.org/W3140964896","doi":null,"title":"Leveraging neural representations for facilitating access to untranscribed speech from endangered languages.","display_name":"Leveraging neural representations for facilitating access to untranscribed speech from endangered languages.","publication_year":2021,"publication_date":"2021-03-26","ids":{"openalex":"https://openalex.org/W3140964896","mag":"3140964896"},"language":"en","primary_location":{"id":"mag:3140964896","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2103.14583","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2103.14583","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","observed_orcids":["https://orcid.org/0000-0002-3533-5025"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nay San","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3533-5025","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033914946","display_name":"Martijn Bartelds","orcid":"https://orcid.org/0000-0003-1006-8669","observed_orcids":["https://orcid.org/0000-0003-1006-8669"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martijn Bartelds","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1006-8669","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088740812","display_name":"Mitchell Browne","orcid":"https://orcid.org/0000-0001-7623-8179","observed_orcids":["https://orcid.org/0000-0001-7623-8179"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitchell Browne","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7623-8179","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082863197","display_name":"Lily Clifford","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lily Clifford","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fiona Gibson","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fiona Gibson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064414060","display_name":"John Mansfield","orcid":"https://orcid.org/0000-0003-1167-1136","observed_orcids":["https://orcid.org/0000-0003-1167-1136"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Mansfield","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1167-1136","affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"David T. Nash","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David T. Nash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027313930","display_name":"Jane Simpson","orcid":"https://orcid.org/0000-0002-7487-1234","observed_orcids":["https://orcid.org/0000-0002-7487-1234"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jane Simpson","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7487-1234","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012693173","display_name":"Myfany Turpin","orcid":"https://orcid.org/0000-0003-0395-6756","observed_orcids":["https://orcid.org/0000-0003-0395-6756"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Myfany Turpin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0395-6756","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081830016","display_name":"Maria Vollmer","orcid":"https://orcid.org/0000-0003-2424-159X","observed_orcids":["https://orcid.org/0000-0003-2424-159X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Vollmer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068304444","display_name":"Sasha Wilmoth","orcid":"https://orcid.org/0000-0002-6626-9104","observed_orcids":["https://orcid.org/0000-0002-6626-9104"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sasha Wilmoth","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6626-9104","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087088138","display_name":"Dan Jurafsky","orcid":"https://orcid.org/0000-0002-6459-7745","observed_orcids":["https://orcid.org/0000-0002-6459-7745"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Jurafsky","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6459-7745","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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":0.00019999999494757503,"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/endangered-languages","display_name":"endangered languages","score":0.9940000176429749},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.8190000057220459},{"id":"https://openalex.org/keywords/pre-trained-language-models","display_name":"pre-trained language models","score":0.5529999732971191},{"id":"https://openalex.org/keywords/cross-lingual-transfer","display_name":"cross-lingual transfer","score":0.6169999837875366},{"id":"https://openalex.org/keywords/phonological-similarity","display_name":"phonological similarity","score":0.7099999785423279},{"id":"https://openalex.org/keywords/australian-aboriginal-languages","display_name":"Aboriginal Australian languages","score":0.7739999890327454},{"id":"https://openalex.org/keywords/dutch","display_name":"Dutch language","score":0.34599998593330383},{"id":"https://openalex.org/keywords/low-resource-speech-recognition","display_name":"low-resource speech recognition","score":0.7279999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8558818101882935},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6144866347312927},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5888011455535889},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5721046924591064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5230116248130798},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.5167721509933472},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.508302628993988},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5059077143669128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4709768295288086},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4633996784687042},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4623587727546692},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.18747225403785706},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.16099095344543457},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.15943852066993713},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.15923503041267395},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3140964896","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2103.14583","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3140964896","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2103.14583","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2088615611","https://openalex.org/W2442329935","https://openalex.org/W2899377381","https://openalex.org/W2957905185","https://openalex.org/W2979476256","https://openalex.org/W3037057938","https://openalex.org/W3099782249","https://openalex.org/W3158394340"],"related_works":["https://openalex.org/W3200887081","https://openalex.org/W2104283211","https://openalex.org/W3035450433","https://openalex.org/W2954282963","https://openalex.org/W3133501470","https://openalex.org/W2242808236","https://openalex.org/W2990013535","https://openalex.org/W98940168","https://openalex.org/W269707310","https://openalex.org/W4384407239"],"abstract_inverted_index":{"For":[0],"languages":[1,70,91],"with":[2,161],"insufficient":[3],"resources":[4],"to":[5,107,167],"train":[6],"speech":[7,22],"recognition":[8],"systems,":[9],"query-by-example":[10],"spoken":[11,29,45],"term":[12],"detection":[13,150,157],"(QbE-STD)":[14],"offers":[15],"a":[16,59,72],"way":[17],"of":[18,61,75,78,110,125],"accessing":[19],"an":[20],"untranscribed":[21],"corpus":[23,43],"by":[24,46,95],"helping":[25],"identify":[26],"regions":[27],"where":[28],"query":[30,41],"terms":[31],"occur.":[32],"Yet":[33],"retrieval":[34],"performance":[35,88,135,158],"can":[36],"be":[37,93],"poor":[38],"when":[39],"the":[40,100,108,122,126,144,153,162],"and":[42,49,63,71,114,138],"are":[44,80],"different":[47,52],"speakers":[48,62],"produced":[50],"in":[51,133],"recording":[53,64],"conditions.":[54],"Using":[55],"data":[56],"selected":[57],"from":[58,66,99,121],"variety":[60,74],"conditions":[65],"7":[67],"Australian":[68],"Aboriginal":[69],"regional":[73],"Dutch,":[76],"all":[77,152],"which":[79],"endangered":[81],"or":[82],"vulnerable,":[83],"we":[84,117],"evaluated":[85],"whether":[86],"QbE-STD":[87],"on":[89,151],"these":[90],"could":[92],"improved":[94,149],"leveraging":[96],"representations":[97,120],"extracted":[98,142],"pre-trained":[101,145],"English":[102,146],"wav2vec":[103,127],"2.0":[104,128],"model.":[105],"Compared":[106],"use":[109],"Mel-frequency":[111],"cepstral":[112],"coefficients":[113],"bottleneck":[115],"features,":[116],"find":[118],"that":[119],"middle":[123],"layers":[124],"Transformer":[129],"offer":[130],"large":[131],"gains":[132],"task":[134],"(between":[136],"56%":[137],"86%).":[139],"While":[140],"features":[141],"using":[143],"model":[147],"yielded":[148],"evaluation":[154,163],"languages,":[155],"better":[156],"was":[159],"associated":[160],"language's":[164],"phonological":[165],"similarity":[166],"English.":[168]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2021-04-13T00:00:00"}