{"id":"https://openalex.org/W3180902893","doi":"https://doi.org/10.1109/asru51503.2021.9687898","title":"Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition","display_name":"Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3180902893","doi":"https://doi.org/10.1109/asru51503.2021.9687898","mag":"3180902893"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687898","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.02268","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050326287","display_name":"Christian Huber","orcid":"https://orcid.org/0000-0001-6518-710X"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christian Huber","raw_affiliation_strings":["Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055254386","display_name":"Juan Hussain","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Juan Hussain","raw_affiliation_strings":["Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065183855","display_name":"Sebastian St\u00fcker","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Stuker","raw_affiliation_strings":["Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023053982","display_name":"Alexander Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Waibel","raw_affiliation_strings":["Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Interactive Systems Lab,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050326287"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.1269,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.33508918,"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/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":0.9993000030517578,"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":0.7952446937561035},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6757455468177795},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6642972230911255},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6578808426856995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6574731469154358},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6376931667327881},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5591750741004944},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5428524017333984},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5197760462760925},{"id":"https://openalex.org/keywords/instant","display_name":"Instant","score":0.43963623046875},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4288121461868286},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1414317786693573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952446937561035},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6757455468177795},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6642972230911255},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6578808426856995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6574731469154358},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6376931667327881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591750741004944},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5428524017333984},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5197760462760925},{"id":"https://openalex.org/C2779432360","wikidata":"https://www.wikidata.org/wiki/Q16963779","display_name":"Instant","level":2,"score":0.43963623046875},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4288121461868286},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1414317786693573},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/asru51503.2021.9687898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687898","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:arXiv.org:2107.02268","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.02268","pdf_url":"https://arxiv.org/pdf/2107.02268","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3180902893","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2107.02268","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.2107.02268","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.02268","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.5445/ir/1000166132","is_oa":true,"landing_page_url":"https://doi.org/10.5445/ir/1000166132","pdf_url":null,"source":{"id":"https://openalex.org/S7407052948","display_name":"KITopen","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.02268","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.02268","pdf_url":"https://arxiv.org/pdf/2107.02268","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G5060757285","display_name":null,"funder_award_id":"01IS18040A,01EF1803B","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3180902893.pdf","grobid_xml":"https://content.openalex.org/works/W3180902893.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W1494198834","https://openalex.org/W2327501763","https://openalex.org/W2399033357","https://openalex.org/W2507756961","https://openalex.org/W2606974598","https://openalex.org/W2744031566","https://openalex.org/W2799473636","https://openalex.org/W2886319145","https://openalex.org/W2899274165","https://openalex.org/W2937402758","https://openalex.org/W2945700568","https://openalex.org/W2950527759","https://openalex.org/W2951008357","https://openalex.org/W2954716088","https://openalex.org/W2963403868","https://openalex.org/W2963792777","https://openalex.org/W2963979492","https://openalex.org/W2970611152","https://openalex.org/W2972320704","https://openalex.org/W2972451902","https://openalex.org/W2972592316","https://openalex.org/W2973122799","https://openalex.org/W2995929068","https://openalex.org/W3011339933","https://openalex.org/W3015889230","https://openalex.org/W3016188195","https://openalex.org/W3092085609","https://openalex.org/W3101648800","https://openalex.org/W3129905227","https://openalex.org/W6600880057","https://openalex.org/W6638318767","https://openalex.org/W6684821475","https://openalex.org/W6712906272","https://openalex.org/W6725207838","https://openalex.org/W6732742072","https://openalex.org/W6739901393","https://openalex.org/W6755559483","https://openalex.org/W6771467084"],"related_works":["https://openalex.org/W2935031511","https://openalex.org/W3207836786","https://openalex.org/W3011026370","https://openalex.org/W3137608412","https://openalex.org/W2884483159","https://openalex.org/W2767906378","https://openalex.org/W2274970128","https://openalex.org/W2405994102","https://openalex.org/W2814989140","https://openalex.org/W1538534294","https://openalex.org/W2109705048","https://openalex.org/W2033266261","https://openalex.org/W139927782","https://openalex.org/W1963734729","https://openalex.org/W2130106985","https://openalex.org/W2407602485","https://openalex.org/W2820862279","https://openalex.org/W2902348614","https://openalex.org/W3087942445","https://openalex.org/W3034343705"],"abstract_inverted_index":{"Neural":[0],"sequence-to-sequence":[1],"systems":[2,21],"deliver":[3],"state-of-the-art":[4],"performance":[5],"for":[6,102],"automatic":[7],"speech":[8],"recognition":[9],"(ASR).":[10],"When":[11],"using":[12],"appropriate":[13],"modeling":[14],"units,":[15],"e.g.,":[16,41],"byte-pair":[17],"encoded":[18],"characters,":[19],"these":[20],"are":[22],"in":[23],"principal":[24],"open":[25],"vocabulary":[26],"systems.":[27],"In":[28,105],"practice,":[29],"however,":[30],"they":[31],"often":[32],"fail":[33],"to":[34,65,69,118,131,134],"recognize":[35,70,119,132],"words":[36,72,126],"not":[37],"seen":[38],"during":[39],"training,":[40],"named":[42],"entities,":[43],"numbers":[44],"or":[45,96],"technical":[46],"terms.":[47],"To":[48],"alleviate":[49],"this":[50,67,106,112],"problem":[51],"we":[52,108],"supplement":[53],"an":[54],"end-to-end":[55],"ASR":[56,81],"system":[57,115],"with":[58],"a":[59,63,90,135],"word/phrase":[60],"memory":[61,68],"and":[62,73,83],"mechanism":[64,113],"access":[66],"the":[71,77,80,100],"phrases":[74],"correctly.":[75],"After":[76],"training":[78],"of":[79,123],"system,":[82],"when":[84],"it":[85,128],"has":[86],"already":[87],"been":[88],"deployed,":[89],"relevant":[91],"word":[92],"can":[93],"be":[94],"added":[95,125],"subtracted":[97],"instantly":[98],"without":[99],"need":[101],"further":[103],"training.":[104],"paper":[107],"demonstrate":[109],"that":[110,127],"through":[111],"our":[114],"is":[116],"able":[117],"more":[120],"than":[121],"85%":[122],"newly":[124],"previously":[129],"failed":[130],"compared":[133],"strong":[136],"baseline.":[137]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}