{"id":"https://openalex.org/W2996631218","doi":"https://doi.org/10.21437/interspeech.2020-1186","title":"Predicting Detection Filters for Small Footprint Open-Vocabulary Keyword Spotting","display_name":"Predicting Detection Filters for Small Footprint Open-Vocabulary Keyword Spotting","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W2996631218","doi":"https://doi.org/10.21437/interspeech.2020-1186","mag":"2996631218"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1186","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1186","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.07575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030191869","display_name":"Th\u00e9odore Bluche","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210088322","display_name":"Centre de Gestion Scientifique","ror":"https://ror.org/003y0kg83","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I142476485","https://openalex.org/I190752583","https://openalex.org/I190752583","https://openalex.org/I205703379","https://openalex.org/I2746051580","https://openalex.org/I2746051580","https://openalex.org/I4210088322","https://openalex.org/I4210091621","https://openalex.org/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4405258429","https://openalex.org/I70768539","https://openalex.org/I70768539"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Th\u00e9odore Bluche","raw_affiliation_strings":["Centre National de la Recherche Scientifique, Paris, France"],"affiliations":[{"raw_affiliation_string":"Centre National de la Recherche Scientifique, Paris, France","institution_ids":["https://openalex.org/I4210088322","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001811190","display_name":"Thibault Gisselbrecht","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thibault Gisselbrecht","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030191869"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210088322"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00935077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2552","last_page":"2556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9820685386657715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8582522869110107},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6543373465538025},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6337684392929077},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6219295859336853},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6114159822463989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5923569202423096},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5301386117935181},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.46199846267700195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45749151706695557},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42900556325912476},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3299481272697449},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2863568961620331},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.17287135124206543}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9820685386657715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582522869110107},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6543373465538025},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6337684392929077},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6219295859336853},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6114159822463989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5923569202423096},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5301386117935181},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.46199846267700195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45749151706695557},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42900556325912476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3299481272697449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2863568961620331},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.17287135124206543},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-1186","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1186","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:1912.07575","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.07575","pdf_url":"https://arxiv.org/pdf/1912.07575","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2996631218","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1912.07575","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.1912.07575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1912.07575","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.07575","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.07575","pdf_url":"https://arxiv.org/pdf/1912.07575","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2996631218.pdf","grobid_xml":"https://content.openalex.org/works/W2996631218.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W210770835","https://openalex.org/W1489125746","https://openalex.org/W1494198834","https://openalex.org/W1982479097","https://openalex.org/W2019318646","https://openalex.org/W2080141381","https://openalex.org/W2127141656","https://openalex.org/W2212465773","https://openalex.org/W2405666970","https://openalex.org/W2407023693","https://openalex.org/W2414711238","https://openalex.org/W2533523411","https://openalex.org/W2558258029","https://openalex.org/W2578392894","https://openalex.org/W2763188033","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2886949521","https://openalex.org/W2898771141","https://openalex.org/W2900914384","https://openalex.org/W2963628261","https://openalex.org/W2964138017","https://openalex.org/W2964187693","https://openalex.org/W2972613398","https://openalex.org/W3007438732","https://openalex.org/W3176896803"],"related_works":["https://openalex.org/W3095694146","https://openalex.org/W3008790380","https://openalex.org/W2186376519","https://openalex.org/W2291708837","https://openalex.org/W3001552705","https://openalex.org/W2954379807","https://openalex.org/W2009071922","https://openalex.org/W2124957963","https://openalex.org/W2184734873","https://openalex.org/W1569293908","https://openalex.org/W2963353710","https://openalex.org/W3189855750","https://openalex.org/W2787371088","https://openalex.org/W2100478624","https://openalex.org/W2281024535","https://openalex.org/W3039834034","https://openalex.org/W1938647619","https://openalex.org/W3156660616","https://openalex.org/W183136171","https://openalex.org/W2158043158"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4,102],"a":[5,18,34,64,81,103,120,124],"fully-neural":[6],"approach":[7],"to":[8,16,22,62,105,123,137,140],"open-vocabulary":[9],"keyword":[10,35,49,77],"spotting,":[11],"that":[12,26,57,71],"allows":[13],"the":[14,45,72,107,132,135],"users":[15],"include":[17],"customizable":[19],"voice":[20],"interface":[21],"their":[23],"device":[24],"and":[25,92],"does":[27],"not":[28],"require":[29],"task-specific":[30],"data.":[31],"We":[32,69,100],"present":[33],"detection":[36,50],"neural":[37,128],"network":[38,129],"weighing":[39],"less":[40],"than":[41],"250KB,":[42],"in":[43,90],"which":[44,118],"topmost":[46],"layer":[47],"performing":[48],"is":[51,113],"predicted":[52],"by":[53,80],"an":[54],"auxiliary":[55],"network,":[56],"may":[58],"be":[59,138],"run":[60],"offline":[61],"generate":[63],"detector":[65],"for":[66,115],"any":[67],"keyword.":[68],"show":[70],"proposed":[73],"model":[74,108,136],"outperforms":[75],"acoustic":[76],"spotting":[78],"baselines":[79],"large":[82],"margin":[83],"on":[84],"two":[85],"tasks":[86,94],"of":[87,95,134],"detecting":[88,96],"keywords":[89],"utterances":[91],"three":[93],"isolated":[97],"speech":[98,126],"commands.":[99],"also":[101],"method":[104],"fine-tune":[106],"when":[109],"specific":[110],"training":[111],"data":[112],"available":[114],"some":[116],"keywords,":[117],"yields":[119],"performance":[121],"similar":[122],"standard":[125],"command":[127],"while":[130],"keeping":[131],"ability":[133],"applied":[139],"new":[141],"keywords.":[142]},"counts_by_year":[],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}
