{"id":"https://openalex.org/W3096664139","doi":"https://doi.org/10.21437/interspeech.2020-1750","title":"Do End-to-End Speech Recognition Models Care About Context?","display_name":"Do End-to-End Speech Recognition Models Care About Context?","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096664139","doi":"https://doi.org/10.21437/interspeech.2020-1750","mag":"3096664139"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1750","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.09928","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018340002","display_name":"Lasse Borgholt","orcid":"https://orcid.org/0000-0002-3562-8442"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Lasse Borgholt","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen, Denmark","Corti, Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]},{"raw_affiliation_string":"Corti, Copenhagen, Denmark","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040069285","display_name":"Jakob D. Havtorn","orcid":"https://orcid.org/0000-0002-4849-0817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakob D. Havtorn","raw_affiliation_strings":["Corti, Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Corti, Copenhagen, Denmark","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090835657","display_name":"\u017beljko Agi\u0107","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u017deljko Agi\u0107","raw_affiliation_strings":["Corti, Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Corti, Copenhagen, Denmark","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018138946","display_name":"Anders S\u00f8gaard","orcid":"https://orcid.org/0000-0001-5250-4276"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Anders S\u00f8gaard","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007556794","display_name":"Lars Maal\u00f8e","orcid":"https://orcid.org/0000-0003-2030-520X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lars Maal\u00f8e","raw_affiliation_strings":["Corti, Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Corti, Copenhagen, Denmark","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042628612","display_name":"Christian Igel","orcid":"https://orcid.org/0000-0003-2868-0856"},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Christian Igel","raw_affiliation_strings":["Department of Computer Science, University of Copenhagen, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042628612"],"corresponding_institution_ids":["https://openalex.org/I124055696"],"apc_list":null,"apc_paid":null,"fwci":1.0824,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83138318,"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":"4352","last_page":"4356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/connectionism","display_name":"Connectionism","score":0.7985682487487793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.768996000289917},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7573674917221069},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6503583788871765},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6324568390846252},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5491823554039001},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5134049654006958},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5085364580154419},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4563813805580139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4298979341983795},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4112461805343628},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3746229112148285},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21145543456077576},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07725483179092407}],"concepts":[{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7985682487487793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.768996000289917},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7573674917221069},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6503583788871765},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6324568390846252},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5491823554039001},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5134049654006958},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5085364580154419},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4563813805580139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4298979341983795},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4112461805343628},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3746229112148285},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21145543456077576},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07725483179092407},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1750","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.09928","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.09928","pdf_url":"https://arxiv.org/pdf/2102.09928","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":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/9cd3f7a6-3cca-4910-8ae2-8929d525649e","is_oa":true,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/9cd3f7a6-3cca-4910-8ae2-8929d525649e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"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":"Borgholt , L , Havtorn , J D , Agic , \u017d , S\u00f8gaard , A , Maal\u00f8e , L & Igel , C 2020 , Do end-to-end speech recognition models care about context? in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH . vol. 2020-October , International Speech Communication Association (ISCA) , pp. 4352-4356 , 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 , Shanghai , China , 25/10/2020 . https://doi.org/10.21437/Interspeech.2020-1750","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.atira.dk:publications/ffe9d76a-5cf0-43cd-ac20-25db6cebb9b3","is_oa":true,"landing_page_url":"https://orbit.dtu.dk/en/publications/ffe9d76a-5cf0-43cd-ac20-25db6cebb9b3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"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":"Borgholt , L , Havtorn , J D , Agic , \u017d , S\u00f8gaard , A , Maal\u00f8e , L & Igel , C 2020 , Do end-to-end speech recognition models care about context? in Proceedings of the Annual Conference of the International Speech Communication Association . Proceedings of the Annual Conference of the International Speech Communication Association, Interspeech , pp. 4352-4356 , Interspeech 2020 , Shanghai , China , 25/10/2020 . https://doi.org/10.21437/Interspeech.2020-1750","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.09928","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.09928","pdf_url":"https://arxiv.org/pdf/2102.09928","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1826234144","https://openalex.org/W1849277567","https://openalex.org/W1936750108","https://openalex.org/W1969404656","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2159778339","https://openalex.org/W2193413348","https://openalex.org/W2327469455","https://openalex.org/W2327501763","https://openalex.org/W2404126548","https://openalex.org/W2530486890","https://openalex.org/W2530876040","https://openalex.org/W2562979205","https://openalex.org/W2577366047","https://openalex.org/W2750499125","https://openalex.org/W2904818793","https://openalex.org/W2914479667","https://openalex.org/W2915253508","https://openalex.org/W2936774411","https://openalex.org/W2951595529","https://openalex.org/W2952288254","https://openalex.org/W2962826786","https://openalex.org/W2963446712","https://openalex.org/W2963742216","https://openalex.org/W2963827914","https://openalex.org/W2964045325","https://openalex.org/W2964121744","https://openalex.org/W2964159778","https://openalex.org/W2964308564","https://openalex.org/W2972376180","https://openalex.org/W2972816482","https://openalex.org/W2973049979","https://openalex.org/W2973215447","https://openalex.org/W3103005696","https://openalex.org/W3127686677","https://openalex.org/W4289440825"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W2916997151","https://openalex.org/W3096664139","https://openalex.org/W4385890381"],"abstract_inverted_index":{"The":[0],"two":[1,89],"most":[2],"common":[3],"paradigms":[4],"for":[5,29],"end-to-end":[6],"speech":[7],"recognition":[8],"are":[9],"connectionist":[10],"temporal":[11,41],"classification":[12],"(CTC)":[13],"and":[14,44,116],"attention-based":[15],"encoder-decoder":[16],"(AED)":[17],"models.":[18],"It":[19],"has":[20],"been":[21],"argued":[22],"that":[23,64,74,107],"the":[24,47,53,59,65,75,84,88,108,119],"latter":[25],"is":[26,68,96,111],"better":[27],"suited":[28],"learning":[30],"an":[31,122],"implicit":[32],"language":[33,124],"model.":[34,86,125],"We":[35,62],"test":[36],"this":[37],"hypothesis":[38],"by":[39,80],"measuring":[40],"context":[42,71],"sensitivity":[43],"evaluate":[45],"how":[46],"models":[48,90],"perform":[49,91],"when":[50,93],"we":[51],"constrain":[52],"amount":[54],"of":[55,121],"contextual":[56,94],"information":[57,95],"in":[58,99],"audio":[60],"input.":[61],"find":[63],"AED":[66],"model":[67,110],"indeed":[69],"more":[70],"sensitive,":[72],"but":[73],"gap":[76],"can":[77],"be":[78],"closed":[79],"adding":[81],"self-attention":[82],"to":[83,101],"CTC":[85,109],"Furthermore,":[87],"similarly":[92],"constrained.":[97],"Finally,":[98],"contrast":[100],"previous":[102],"research,":[103],"our":[104],"results":[105],"show":[106],"highly":[112],"competitive":[113],"on":[114],"WSJ":[115],"LibriSpeech":[117],"without":[118],"help":[120],"external":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}