{"id":"https://openalex.org/W7141852512","doi":"https://doi.org/10.1016/j.csl.2026.101986","title":"Open-vocabulary keyword spotting with hyper-matched filters for small footprint devices","display_name":"Open-vocabulary keyword spotting with hyper-matched filters for small footprint devices","publication_year":2026,"publication_date":"2026-03-28","ids":{"openalex":"https://openalex.org/W7141852512","doi":"https://doi.org/10.1016/j.csl.2026.101986","pmid":"https://pubmed.ncbi.nlm.nih.gov/42005703"},"language":"en","primary_location":{"id":"doi:10.1016/j.csl.2026.101986","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.101986","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.csl.2026.101986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130841924","display_name":"Yael Segal-Feldman","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Yael Segal-Feldman","raw_affiliation_strings":["Faculty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel"],"raw_orcid":"https://orcid.org/0000-0003-2513-0752","affiliations":[{"raw_affiliation_string":"Faculty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009503530","display_name":"Ann R. Bradlow","orcid":"https://orcid.org/0000-0001-5560-6059"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ann R. Bradlow","raw_affiliation_strings":["Department of Linguistics, Northwestern University, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, Northwestern University, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026401498","display_name":"Matthew Goldrick","orcid":"https://orcid.org/0000-0002-2035-416X"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Goldrick","raw_affiliation_strings":["Department of Linguistics, Northwestern University, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, Northwestern University, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130839806","display_name":"Joseph Keshet","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["Faculty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel"],"raw_orcid":"https://orcid.org/0000-0003-2332-5783","affiliations":[{"raw_affiliation_string":"Faculty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5130841924"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":{"value":3400,"currency":"USD","value_usd":3400},"apc_paid":{"value":3400,"currency":"USD","value_usd":3400},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33279299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"100","issue":null,"first_page":"101986","last_page":"101986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.26010000705718994,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.26010000705718994,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.09920000284910202,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.05139999836683273,"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/keyword-spotting","display_name":"Keyword spotting","score":0.8708000183105469},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.6967999935150146},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6150000095367432},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3481000065803528},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.34060001373291016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9215999841690063},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8708000183105469},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.6967999935150146},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6150000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4927000105381012},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.385699987411499},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33739998936653137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2597000002861023}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.csl.2026.101986","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.101986","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"},{"id":"pmid:42005703","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42005703","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer speech & language","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13089972","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13089972/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Comput Speech Lang","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1016/j.csl.2026.101986","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2026.101986","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech & Language","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5595541596412659,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7881582439","display_name":null,"funder_award_id":"MH134369","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320323706","display_name":"Ministry of Science and Technology, Israel","ror":"https://ror.org/02heb2n75"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1982479097","https://openalex.org/W2127141656","https://openalex.org/W2151244813","https://openalex.org/W2151305291","https://openalex.org/W2972613398","https://openalex.org/W3019293601","https://openalex.org/W3095012737","https://openalex.org/W3095694146","https://openalex.org/W4206567542","https://openalex.org/W4319300692","https://openalex.org/W4400187963","https://openalex.org/W4402727368"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"keyword":[1,31,51,71,82],"spotting":[2,32],"(KWS)":[3],"refers":[4],"to":[5,114,151],"the":[6,23,80,111,121,131,136],"task":[7],"of":[8,17,45,92,124],"detecting":[9],"words":[10],"or":[11,65,168],"terms":[12],"within":[13],"speech":[14,47,58],"recordings,":[15],"regardless":[16],"whether":[18,130],"they":[19],"were":[20],"included":[21],"in":[22,128,135],"training":[24],"data.":[25],"This":[26],"paper":[27],"introduces":[28],"an":[29],"open-vocabulary":[30],"model":[33,42],"with":[34,162],"state-of-the-art":[35,145],"detection":[36,55,108,146],"accuracy":[37],"for":[38,94],"small-footprint":[39],"devices.":[40],"The":[41,57,69,107,138],"is":[43,60,73],"composed":[44],"a":[46,49,54,62,66,76,84,89,95,103,116,125],"encoder,":[48,52],"target":[50,70,132],"and":[53,87,148,179],"network.":[56],"encoder":[59,72],"either":[61],"tiny":[63,67],"Whisper":[64],"Conformer.":[68],"implemented":[74],"as":[75,83,102],"hyper-network":[77],"that":[78,141,171],"takes":[79],"desired":[81],"character":[85],"string":[86],"generates":[88],"unique":[90],"set":[91],"weights":[93,113],"convolutional":[96],"layer,":[97],"which":[98,119],"can":[99],"be":[100],"considered":[101],"keyword-specific":[104,117],"matched":[105],"filter.":[106],"network":[109],"uses":[110],"matched-filter":[112],"perform":[115],"convolution,":[118],"guides":[120],"cross-attention":[122],"mechanism":[123],"Perceiver":[126],"module":[127],"determining":[129],"term":[133],"appears":[134],"recording.":[137],"results":[139],"indicate":[140],"our":[142,159],"system":[143],"achieves":[144],"performance":[147],"generalizes":[149],"effectively":[150],"out-of-domain":[152],"conditions,":[153],"including":[154],"second-language":[155],"(L2)":[156],"speech.":[157],"Notably,":[158],"smallest":[160],"model,":[161],"just":[163],"4.2":[164],"million":[165],"parameters,":[166],"matches":[167],"outperforms":[169],"models":[170],"are":[172],"several":[173],"times":[174],"larger,":[175],"demonstrating":[176],"both":[177],"efficiency":[178],"robustness.":[180]},"counts_by_year":[],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2026-03-29T00:00:00"}