{"id":"https://openalex.org/W3131172781","doi":"https://doi.org/10.1109/icassp39728.2021.9414298","title":"Meta-Learning for Improving Rare Word Recognition in End-to-End ASR","display_name":"Meta-Learning for Improving Rare Word Recognition in End-to-End ASR","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3131172781","doi":"https://doi.org/10.1109/icassp39728.2021.9414298","mag":"3131172781"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/2102.12624","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078880407","display_name":"Florian Lux","orcid":"https://orcid.org/0000-0003-4325-5129"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Lux","raw_affiliation_strings":["University of Stuttgart Institute for Natural Language Processing, Stuttgart, Germany","University of Stuttgart Institute for Natural Language Processing,Stuttgart,Germany,70569"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart Institute for Natural Language Processing, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart Institute for Natural Language Processing,Stuttgart,Germany,70569","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":["University of Stuttgart Institute for Natural Language Processing, Stuttgart, Germany","University of Stuttgart Institute for Natural Language Processing,Stuttgart,Germany,70569"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stuttgart Institute for Natural Language Processing, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"University of Stuttgart Institute for Natural Language Processing,Stuttgart,Germany,70569","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2799,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61578977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"5974","last_page":"5978"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/T12031","display_name":"Speech and dialogue systems","score":0.9864000082015991,"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/spotting","display_name":"Spotting","score":0.9171199798583984},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8414613604545593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8198914527893066},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.720950186252594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.694192111492157},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6248357892036438},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4653201103210449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.453016072511673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3812618851661682}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.9171199798583984},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8414613604545593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198914527893066},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.720950186252594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.694192111492157},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6248357892036438},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4653201103210449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453016072511673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3812618851661682},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.12624","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12624","pdf_url":"https://arxiv.org/pdf/2102.12624","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":"","raw_type":"text"},{"id":"mag:3131172781","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.12624.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.2102.12624","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.12624","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:10.17023/137w-rx97","is_oa":true,"landing_page_url":"https://doi.org/10.17023/137w-rx97","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:2102.12624","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.12624","pdf_url":"https://arxiv.org/pdf/2102.12624","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3131172781.pdf","grobid_xml":"https://content.openalex.org/works/W3131172781.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2034940213","https://openalex.org/W2064675550","https://openalex.org/W2081470342","https://openalex.org/W2102113734","https://openalex.org/W2127589108","https://openalex.org/W2138621090","https://openalex.org/W2144935315","https://openalex.org/W2161914416","https://openalex.org/W2601450892","https://openalex.org/W2892009249","https://openalex.org/W2898599211","https://openalex.org/W2901607128","https://openalex.org/W2903739847","https://openalex.org/W2916997151","https://openalex.org/W2962780374","https://openalex.org/W2963341924","https://openalex.org/W2963403868","https://openalex.org/W2963425185","https://openalex.org/W2964105864","https://openalex.org/W2964308564","https://openalex.org/W2968021853","https://openalex.org/W2972818416","https://openalex.org/W2973072704","https://openalex.org/W3015470971","https://openalex.org/W3016160783","https://openalex.org/W3032859754","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6680962578","https://openalex.org/W6683825394","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6739901393","https://openalex.org/W6750665317","https://openalex.org/W6767005581"],"related_works":["https://openalex.org/W3161525333","https://openalex.org/W3102259066","https://openalex.org/W2963658982","https://openalex.org/W2916685081","https://openalex.org/W1561056154","https://openalex.org/W3016042119","https://openalex.org/W2404988390","https://openalex.org/W3148101939","https://openalex.org/W2599118679","https://openalex.org/W2950548836","https://openalex.org/W2550975896","https://openalex.org/W3093427098","https://openalex.org/W3094180720","https://openalex.org/W2884454321","https://openalex.org/W2808935172","https://openalex.org/W2972592316","https://openalex.org/W2886319145","https://openalex.org/W2986416418","https://openalex.org/W3161539047","https://openalex.org/W3207460178"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,133],"take":[4],"on":[5],"the":[6,69,101,105,111,122,125],"challenge":[7],"of":[8,38,71,73,86,124],"rare":[9],"word":[10,139],"recognition":[11,17],"in":[12,62,77,94,104],"end-to-end":[13],"(E2E)":[14],"automatic":[15],"speech":[16,106,131],"(ASR)":[18],"by":[19,142],"integrating":[20],"a":[21,35,95],"meta":[22,46,113],"learning":[23,47,114],"mechanism":[24],"into":[25],"an":[26,56,63],"E2E":[27,64],"ASR":[28,65],"system,":[29],"enabling":[30,49],"few-shot":[31,96],"adaptation.":[32],"We":[33,67,98],"propose":[34],"novel":[36],"method":[37],"generating":[39],"embeddings":[40,107],"for":[41,83],"speech,":[42],"changes":[43],"to":[44,51,58,109,116,136,144],"four":[45],"approaches,":[48],"them":[50],"perform":[52,117],"keyword":[53,128],"spotting":[54,129],"and":[55,89,130],"approach":[57],"using":[59],"their":[60,81],"outcomes":[61],"system.":[66],"verify":[68],"functionality":[70],"each":[72],"our":[74],"three":[75],"contributions":[76],"two":[78],"experiments":[79],"exploring":[80],"performance":[82],"different":[84],"amounts":[85],"classes":[87],"(N-way)":[88],"examples":[90],"per":[91],"class":[92],"(k-shot)":[93],"setting.":[97],"find":[99],"that":[100],"information":[102],"encoded":[103],"suffices":[108],"allow":[110],"modified":[112],"approaches":[115],"continuous":[118],"signal":[119],"spotting.":[120],"Despite":[121],"simplicity":[123],"interface":[126],"between":[127],"recognition,":[132],"are":[134],"able":[135],"consistently":[137],"improve":[138],"error":[140],"rate":[141],"up":[143],"5%.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}