{"id":"https://openalex.org/W2794999731","doi":"https://doi.org/10.21437/interspeech.2018-1326","title":"Low-Resource Speech-to-Text Translation","display_name":"Low-Resource Speech-to-Text Translation","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2794999731","doi":"https://doi.org/10.21437/interspeech.2018-1326","mag":"2794999731"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1326","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/1803.09164","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Sameer Bansal","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, United States"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, United States","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109031255","display_name":"Adam Lopez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adam Lopez","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005109836"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.8462,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79866554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1298","last_page":"1302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8378912806510925},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6514456272125244},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6264853477478027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5430315732955933},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5291241407394409},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5019676685333252},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5009832382202148},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.493583083152771},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4851177930831909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4673213064670563},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4311266541481018},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.41651827096939087},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07455357909202576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8378912806510925},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6514456272125244},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6264853477478027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5430315732955933},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5291241407394409},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5019676685333252},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5009832382202148},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.493583083152771},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4851177930831909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4673213064670563},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4311266541481018},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.41651827096939087},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07455357909202576},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2018-1326","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.09164","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.09164","pdf_url":"https://arxiv.org/pdf/1803.09164","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/0f39a6b3-7400-40e4-a24d-2ccf23cb873f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/0f39a6b3-7400-40e4-a24d-2ccf23cb873f","pdf_url":"https://www.research.ed.ac.uk/files/64209749/low_resource_speech_to_text_translation_2018.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":"Bansal, S, Kamper, H, Livescu, K, Lopez, A & Goldwater, S 2018, Low-Resource Speech-to-Text Translation. in Proceedings of Interspeech 2018. Proc. Interspeech 2018, Hyderabad, India, pp. 1298-1302, Interspeech 2018, Hyderabad, India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-1326","raw_type":"contributionToPeriodical"},{"id":"mag:2794999731","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1803.09164","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.1803.09164","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.09164","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.09164","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.09164","pdf_url":"https://arxiv.org/pdf/1803.09164","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":0.5199999809265137,"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":30,"referenced_works":["https://openalex.org/W1545920196","https://openalex.org/W1902237438","https://openalex.org/W2016589492","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2101105183","https://openalex.org/W2101281673","https://openalex.org/W2124807415","https://openalex.org/W2133512280","https://openalex.org/W2150622104","https://openalex.org/W2212703438","https://openalex.org/W2291469555","https://openalex.org/W2466918907","https://openalex.org/W2513832136","https://openalex.org/W2516890051","https://openalex.org/W2525145252","https://openalex.org/W2563850823","https://openalex.org/W2593011301","https://openalex.org/W2756675017","https://openalex.org/W2785350307","https://openalex.org/W2786891429","https://openalex.org/W2788575190","https://openalex.org/W2949117887","https://openalex.org/W2950613790","https://openalex.org/W2953118818","https://openalex.org/W2953320089","https://openalex.org/W2962784628","https://openalex.org/W2963767893","https://openalex.org/W3012492057","https://openalex.org/W3167238645"],"related_works":["https://openalex.org/W2963834942","https://openalex.org/W2403234505","https://openalex.org/W3210685431","https://openalex.org/W2995732811","https://openalex.org/W2884989221","https://openalex.org/W2920819083","https://openalex.org/W2550975896","https://openalex.org/W3166538612","https://openalex.org/W3211815492","https://openalex.org/W3134796415","https://openalex.org/W3082845185","https://openalex.org/W3155772857","https://openalex.org/W3203040546","https://openalex.org/W217765821","https://openalex.org/W3170430518","https://openalex.org/W2938099940","https://openalex.org/W3162345085","https://openalex.org/W3008613924","https://openalex.org/W2952127920","https://openalex.org/W1566315437"],"abstract_inverted_index":{"Speech-to-text":[0],"translation":[1,19],"has":[2,41],"many":[3],"potential":[4],"applications":[5],"for":[6,36,60,160,172,184],"low-resource":[7,37,186],"languages,":[8],"but":[9],"the":[10,24,58,81,173],"typical":[11],"approach":[12,67,82],"of":[13,132,167],"cascading":[14],"speech":[15,30,53],"recognition":[16],"with":[17,111,153],"machine":[18],"is":[20],"often":[21],"impossible,":[22],"since":[23],"transcripts":[25],"needed":[26],"to":[27,49,94,109],"train":[28,110],"a":[29,90,161],"recognizer":[31],"are":[32,77],"usually":[33],"not":[34],"available":[35],"languages.":[38],"Recent":[39],"work":[40],"found":[42],"that":[43,99,106,136],"neural":[44],"encoder-decoder":[45],"models":[46,124,138],"can":[47,149],"learn":[48],"directly":[50],"translate":[51],"foreign":[52],"in":[54,70],"high-resource":[55],"scenarios,":[56],"without":[57],"need":[59],"intermediate":[61],"transcription.":[62],"We":[63,97,122],"investigate":[64],"whether":[65],"this":[66,100],"also":[68],"works":[69],"settings":[71],"where":[72],"both":[73],"data":[74,142],"and":[75,129,134,157],"computation":[76],"limited.":[78],"To":[79],"make":[80,85],"efficient,":[83],"we":[84],"several":[86],"architectural":[87],"changes,":[88],"including":[89],"change":[91],"from":[92],"character-level":[93],"word-level":[95],"decoding.":[96],"find":[98,135],"choice":[101],"yields":[102],"crucial":[103],"speed":[104],"improvements":[105],"allow":[107],"us":[108],"fewer":[112],"computational":[113],"resources,":[114],"yet":[115],"still":[116,150,181],"performs":[117],"well":[118],"on":[119,126,140,164],"frequent":[120],"words.":[121],"explore":[123],"trained":[125,139,163],"between":[127],"20":[128],"160":[130,175],"hours":[131,166],"data,":[133,168],"although":[137],"less":[141],"have":[143],"considerably":[144],"lower":[145],"BLEU":[146],"scores,":[147],"they":[148,179],"predict":[151],"words":[152],"relatively":[154],"high":[155],"precision":[156],"recall---around":[158],"50%":[159],"model":[162],"50":[165],"versus":[169],"around":[170],"60%":[171],"full":[174],"hour":[176],"model.":[177],"Thus,":[178],"may":[180],"be":[182],"useful":[183],"some":[185],"scenarios.":[187]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}