{"id":"https://openalex.org/W3141838378","doi":"https://doi.org/10.21437/interspeech.2021-1286","title":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","display_name":"Keyword Transformer: A Self-Attention Model for Keyword Spotting","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3141838378","doi":"https://doi.org/10.21437/interspeech.2021-1286","mag":"3141838378"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1286","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.00769","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025118280","display_name":"Axel Berg","orcid":"https://orcid.org/0000-0003-4401-989X"},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Axel Berg","raw_affiliation_strings":["Lund University, Lund, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University, Lund, Sweden","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110106480","display_name":"Mark O\u2019Connor","orcid":null},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mark O\u2019Connor","raw_affiliation_strings":["Lund University, Lund, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University, Lund, Sweden","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067294823","display_name":"Miguel Tairum Cruz","orcid":"https://orcid.org/0000-0003-0606-602X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miguel Tairum Cruz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4653,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84760763,"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":"4249","last_page":"4253"},"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8833498954772949},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8074679374694824},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7502657175064087},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6740550994873047},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4972861111164093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47346821427345276},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4617716073989868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46055495738983154},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.45822274684906006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37456613779067993},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07329040765762329}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8833498954772949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8074679374694824},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7502657175064087},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6740550994873047},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4972861111164093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47346821427345276},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4617716073989868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46055495738983154},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.45822274684906006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37456613779067993},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07329040765762329},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1286","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.00769","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00769","pdf_url":"https://arxiv.org/pdf/2104.00769","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"mag:3141838378","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2104.00769.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"pmh:oai:lup.lub.lu.se:e40ec581-1249-4263-9b7a-2113427f6f05","is_oa":false,"landing_page_url":"https://lup.lub.lu.se/record/e40ec581-1249-4263-9b7a-2113427f6f05","pdf_url":null,"source":{"id":"https://openalex.org/S4306400536","display_name":"Lund University Publications (Lund University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I187531555","host_organization_name":"Lund University","host_organization_lineage":["https://openalex.org/I187531555"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech; pp 4249-4253 (2021)","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.48550/arxiv.2104.00769","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.00769","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.00769","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00769","pdf_url":"https://arxiv.org/pdf/2104.00769","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2148154194","https://openalex.org/W2194775991","https://openalex.org/W2462831000","https://openalex.org/W2594230395","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2888641632","https://openalex.org/W2899663614","https://openalex.org/W2936774411","https://openalex.org/W2963403868","https://openalex.org/W2973226577","https://openalex.org/W2979636403","https://openalex.org/W3015298864","https://openalex.org/W3015399080","https://openalex.org/W3025165719","https://openalex.org/W3025581723","https://openalex.org/W3035160371","https://openalex.org/W3037953478","https://openalex.org/W3041561163","https://openalex.org/W3094502228","https://openalex.org/W3095321517","https://openalex.org/W3096609285","https://openalex.org/W3097018422","https://openalex.org/W3116489684","https://openalex.org/W3119913666","https://openalex.org/W3121523901","https://openalex.org/W3126337037","https://openalex.org/W3128337785","https://openalex.org/W3159727696","https://openalex.org/W3161873870","https://openalex.org/W3163237592"],"related_works":["https://openalex.org/W3198035615","https://openalex.org/W2964323211","https://openalex.org/W3202223680","https://openalex.org/W3032401935","https://openalex.org/W2003910270","https://openalex.org/W2918559346","https://openalex.org/W2543184722","https://openalex.org/W3142087371","https://openalex.org/W1968431955","https://openalex.org/W3163571828","https://openalex.org/W2962802801","https://openalex.org/W3018114492","https://openalex.org/W3082089446","https://openalex.org/W3015639015","https://openalex.org/W35710827","https://openalex.org/W2981289613","https://openalex.org/W3203633372","https://openalex.org/W3015399080","https://openalex.org/W3131172781","https://openalex.org/W2543727760"],"abstract_inverted_index":{"The":[0],"Transformer":[1,42,51],"architecture":[2,43,56,73],"has":[3,22],"been":[4,24],"successful":[5],"across":[6,61],"many":[7],"domains,":[8],"including":[9],"natural":[10],"language":[11],"processing,":[12],"computer":[13],"vision":[14],"and":[15,47,82,109,115],"speech":[16],"recognition.":[17],"In":[18],"keyword":[19,45],"spotting,":[20],"self-attention":[21],"primarily":[23],"used":[25,88],"on":[26,101,112],"top":[27],"of":[28,37],"convolutional":[29],"or":[30,67],"recurrent":[31,81],"encoders.":[32],"We":[33],"investigate":[34],"a":[35,53,90],"range":[36],"ways":[38],"to":[39,44],"adapt":[40],"the":[41,49,102,113],"spotting":[46],"introduce":[48],"Keyword":[50],"(KWT),":[52],"fully":[54],"self-attentional":[55],"that":[57,78],"exceeds":[58],"state-of-the-art":[59],"performance":[60],"multiple":[62],"tasks":[63,117],"without":[64],"any":[65],"pre-training":[66],"additional":[68],"data.":[69],"Surprisingly,":[70],"this":[71],"simple":[72],"outperforms":[74],"more":[75],"complex":[76],"models":[77],"mix":[79],"convolutional,":[80],"attentive":[83],"layers.":[84],"KWT":[85],"can":[86],"be":[87],"as":[89],"drop-in":[91],"replacement":[92],"for":[93],"these":[94],"models,":[95],"setting":[96],"two":[97],"new":[98],"benchmark":[99],"records":[100],"Google":[103],"Speech":[104],"Commands":[105],"dataset":[106],"with":[107],"98.6%":[108],"97.7%":[110],"accuracy":[111],"12":[114],"35-command":[116],"respectively.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}