{"id":"https://openalex.org/W2981622296","doi":"https://doi.org/10.1109/icassp40776.2020.9053847","title":"Analyzing ASR Pretraining for Low-Resource Speech-to-Text Translation","display_name":"Analyzing ASR Pretraining for Low-Resource Speech-to-Text Translation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981622296","doi":"https://doi.org/10.1109/icassp40776.2020.9053847","mag":"2981622296"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.10762","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081925370","display_name":"Mihaela C. Stoian","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mihaela C. Stoian","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK","[University of Edinburgh,School of Informatics,UK]"],"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[University of Edinburgh,School of Informatics,UK]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005109836","display_name":"Sameer Bansal","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sameer Bansal","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK","[University of Edinburgh,School of Informatics,UK]"],"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[University of Edinburgh,School of Informatics,UK]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics, University of Edinburgh, UK","[University of Edinburgh,School of Informatics,UK]"],"affiliations":[{"raw_affiliation_string":"School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[University of Edinburgh,School of Informatics,UK]","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081925370"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.2718,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62099917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7909","last_page":"7913"},"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/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/T10028","display_name":"Topic Modeling","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7471883296966553},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6511510014533997},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6412896513938904},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6212961077690125},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6005171537399292},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5368983745574951},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5250192284584045},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5149860978126526},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5091421008110046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.500629186630249},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.43234190344810486},{"id":"https://openalex.org/keywords/yield","display_name":"Yield (engineering)","score":0.4125673770904541},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1571948528289795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7471883296966553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6511510014533997},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6412896513938904},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6212961077690125},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6005171537399292},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5368983745574951},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5250192284584045},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5149860978126526},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5091421008110046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.500629186630249},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.43234190344810486},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.4125673770904541},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1571948528289795},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.10762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10762","pdf_url":"https://arxiv.org/pdf/1910.10762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/e1441c27-e014-4163-84f1-98baaed2ea26","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/e1441c27-e014-4163-84f1-98baaed2ea26","pdf_url":"https://www.research.ed.ac.uk/files/134697376/Analyzing_ASR_Pretraining_STOIAN_DOA24012020_AFV.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Stoian, M C, Bansal, S & Goldwater, S 2020, Analyzing ASR Pretraining for Low-Resource Speech-to-Text Translation. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 7909-7913, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9053847","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/e1441c27-e014-4163-84f1-98baaed2ea26","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/e1441c27-e014-4163-84f1-98baaed2ea26","pdf_url":"https://www.research.ed.ac.uk/en/publications/e1441c27-e014-4163-84f1-98baaed2ea26","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Stoian, M C, Bansal, S & Goldwater, S 2020, Analyzing ASR Pretraining for Low-Resource Speech-to-Text Translation. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 7909-7913, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9053847","raw_type":"contributionToPeriodical"},{"id":"mag:2981622296","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.10762.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"doi:10.48550/arxiv.1910.10762","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.10762","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/h3a0-8g64","is_oa":true,"landing_page_url":"https://doi.org/10.17023/h3a0-8g64","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.10762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10762","pdf_url":"https://arxiv.org/pdf/1910.10762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1885850273","display_name":null,"funder_award_id":"Scholar","funder_id":"https://openalex.org/F4320306183","funder_display_name":"James S. McDonnell Foundation"}],"funders":[{"id":"https://openalex.org/F4320306183","display_name":"James S. McDonnell Foundation","ror":"https://ror.org/03dy4aq19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W66627554","https://openalex.org/W1524333225","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1902237438","https://openalex.org/W2016589492","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2407080277","https://openalex.org/W2525778437","https://openalex.org/W2582956876","https://openalex.org/W2605131327","https://openalex.org/W2791647162","https://openalex.org/W2808640845","https://openalex.org/W2894835365","https://openalex.org/W2936969148","https://openalex.org/W2945286432","https://openalex.org/W2962784628","https://openalex.org/W2962813140","https://openalex.org/W2963242190","https://openalex.org/W2963266340","https://openalex.org/W2963292011","https://openalex.org/W2963430224","https://openalex.org/W2963431393","https://openalex.org/W2963678298","https://openalex.org/W2963779652","https://openalex.org/W2963834942","https://openalex.org/W2964104866","https://openalex.org/W2964121744","https://openalex.org/W2964172053","https://openalex.org/W2964309797","https://openalex.org/W3105242324","https://openalex.org/W4300558631","https://openalex.org/W6602682705","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6688167117","https://openalex.org/W6713762819","https://openalex.org/W6743489131","https://openalex.org/W6744702808","https://openalex.org/W6752630080","https://openalex.org/W6786045457","https://openalex.org/W6890288937","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3201659743","https://openalex.org/W3044483536","https://openalex.org/W2145944407","https://openalex.org/W3003809177","https://openalex.org/W3111720488","https://openalex.org/W3133090729","https://openalex.org/W2935924234","https://openalex.org/W2899439440","https://openalex.org/W3171638953","https://openalex.org/W3199610983","https://openalex.org/W2939069254","https://openalex.org/W1614943","https://openalex.org/W3193959417","https://openalex.org/W3175621790","https://openalex.org/W2799800213","https://openalex.org/W3157998614","https://openalex.org/W3161324588","https://openalex.org/W1538434507","https://openalex.org/W2742347851","https://openalex.org/W3197681820"],"abstract_inverted_index":{"Previous":[0],"work":[1],"has":[2],"shown":[3],"that":[4,89,108,131],"for":[5,139],"low-resource":[6],"source":[7,85],"languages,":[8],"automatic":[9,22],"speech-to-text":[10],"translation":[11],"(AST)":[12],"can":[13,56],"be":[14,57],"improved":[15],"by":[16],"pre-training":[17],"an":[18],"end-to-end":[19],"model":[20],"on":[21,72],"speech":[23],"recognition":[24],"(ASR)":[25],"data":[26,47,65,134],"from":[27],"a":[28],"high-resource":[29],"language.":[30,86],"However,":[31],"it":[32],"is":[33,97,118],"not":[34],"clear":[35],"what":[36],"factors":[37],"-":[38,48],"e.g.,":[39],"language":[40],"relatedness":[41],"or":[42,53],"size":[43],"of":[44,74,93,102,125],"the":[45,50,83,90,98,103,121],"pretraining":[46,55,71,132],"yield":[49,136],"biggest":[51],"improvements,":[52],"whether":[54],"effectively":[58],"combined":[59],"with":[60,70,114],"other":[61],"methods":[62],"such":[63],"as":[64],"augmentation.":[66],"Here,":[67],"we":[68],"experiment":[69],"datasets":[73],"varying":[75],"sizes,":[76],"including":[77],"languages":[78],"related":[79],"and":[80,107,133],"unrelated":[81],"to":[82],"AST":[84,95],"We":[87,128],"find":[88],"best":[91],"predictor":[92],"final":[94],"performance":[96,112],"word":[99],"error":[100],"rate":[101],"pretrained":[104],"ASR":[105],"model,":[106],"differences":[109],"in":[110,120],"ASR/AST":[111],"correlate":[113],"how":[115],"phonetic":[116],"information":[117],"encoded":[119],"later":[122],"RNN":[123],"layers":[124],"our":[126],"model.":[127],"also":[129],"show":[130],"augmentation":[135],"complementary":[137],"benefits":[138],"AST.":[140]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-10T06:02:16.177343","created_date":"2025-10-10T00:00:00"}