{"id":"https://openalex.org/W3002801003","doi":"https://doi.org/10.1109/icassp40776.2020.9054039","title":"Learning to Detect Keyword Parts and Whole by Smoothed Max Pooling","display_name":"Learning to Detect Keyword Parts and Whole by Smoothed Max Pooling","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3002801003","doi":"https://doi.org/10.1109/icassp40776.2020.9054039","mag":"3002801003"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/2001.09246","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100328513","display_name":"Hyunjin Park","orcid":"https://orcid.org/0000-0001-5681-8918"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hyun-Jin Park","raw_affiliation_strings":["Google Inc","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059967001","display_name":"Patrick Violette","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Violette","raw_affiliation_strings":["Google Inc","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021522143","display_name":"Niranjan Subrahmanya","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niranjan Subrahmanya","raw_affiliation_strings":["Google Inc","Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100328513"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.2721,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62057883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7899","last_page":"7903"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9975000023841858,"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/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.9808560013771057},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8508737087249756},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7573021650314331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6077577471733093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5767163634300232},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5121681690216064},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5106077790260315},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49865150451660156},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4720288813114166},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46203234791755676},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.43730270862579346},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.412637859582901},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3535136580467224}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9808560013771057},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8508737087249756},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7573021650314331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6077577471733093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5767163634300232},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5121681690216064},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5106077790260315},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49865150451660156},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4720288813114166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46203234791755676},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.43730270862579346},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.412637859582901},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3535136580467224},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.09246","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09246","pdf_url":"https://arxiv.org/pdf/2001.09246","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":"","raw_type":"text"},{"id":"mag:3002801003","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.09246.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.2001.09246","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.09246","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"},{"id":"doi:10.17023/4npv-xg31","is_oa":true,"landing_page_url":"https://doi.org/10.17023/4npv-xg31","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:2001.09246","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09246","pdf_url":"https://arxiv.org/pdf/2001.09246","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3002801003.pdf","grobid_xml":"https://content.openalex.org/works/W3002801003.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W2034940213","https://openalex.org/W2127141656","https://openalex.org/W2296748324","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2587529061","https://openalex.org/W2748659049","https://openalex.org/W2754134153","https://openalex.org/W2775572503","https://openalex.org/W2787752687","https://openalex.org/W2797759721","https://openalex.org/W2891722048","https://openalex.org/W2896422817","https://openalex.org/W2962707338","https://openalex.org/W2962760690","https://openalex.org/W2963977978","https://openalex.org/W2972482531","https://openalex.org/W3098773154","https://openalex.org/W4292084264","https://openalex.org/W6714171909","https://openalex.org/W6744105228","https://openalex.org/W6747003534","https://openalex.org/W6755691404","https://openalex.org/W6756319913"],"related_works":["https://openalex.org/W1572667543","https://openalex.org/W883669783","https://openalex.org/W2151244813","https://openalex.org/W2765157699","https://openalex.org/W2145978959","https://openalex.org/W2827311432","https://openalex.org/W2365305442","https://openalex.org/W3015899119","https://openalex.org/W2766204198","https://openalex.org/W1856119614","https://openalex.org/W3007913012","https://openalex.org/W2509658457","https://openalex.org/W2384379850","https://openalex.org/W3016238098","https://openalex.org/W2000885660","https://openalex.org/W3097246512","https://openalex.org/W2004409624","https://openalex.org/W2811191571","https://openalex.org/W3194502352","https://openalex.org/W2029733119"],"abstract_inverted_index":{"We":[0],"propose":[1],"smoothed":[2],"max":[3],"pooling":[4],"loss":[5,38],"and":[6,24,47],"its":[7],"application":[8],"to":[9,44,81,96],"keyword":[10,22,75],"spotting":[11,76],"systems.":[12],"The":[13,35,69],"proposed":[14,36,70],"approach":[15],"jointly":[16],"trains":[17],"an":[18],"encoder":[19],"(to":[20,27],"detect":[21,28,45],"parts)":[23],"a":[25,32,42,50],"decoder":[26],"whole":[29,48],"keyword)":[30],"in":[31,78],"semi-supervised":[33],"manner.":[34],"new":[37],"function":[39],"allows":[40],"training":[41],"model":[43,77],"parts":[46],"of":[49],"keyword,":[51],"without":[52],"strictly":[53],"depending":[54],"on":[55,99],"frame-level":[56],"labeling":[57],"from":[58],"LVCSR":[59],"(Large":[60],"vocabulary":[61],"continuous":[62],"speech":[63],"recognition),":[64],"making":[65],"further":[66],"optimization":[67],"possible.":[68],"system":[71],"outperforms":[72],"the":[73],"baseline":[74],"[1]":[79],"due":[80,95],"increased":[82],"optimizability.":[83],"Further,":[84],"it":[85],"can":[86],"be":[87],"more":[88],"easily":[89],"adapted":[90],"for":[91],"on-device":[92],"learning":[93],"applications":[94],"reduced":[97],"dependency":[98],"LVCSR.":[100]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}