{"id":"https://openalex.org/W3019293601","doi":"https://doi.org/10.21437/interspeech.2020-1045","title":"Depthwise Separable Convolutional ResNet with Squeeze-and-Excitation Blocks for Small-Footprint Keyword Spotting","display_name":"Depthwise Separable Convolutional ResNet with Squeeze-and-Excitation Blocks for Small-Footprint Keyword Spotting","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3019293601","doi":"https://doi.org/10.21437/interspeech.2020-1045","mag":"3019293601"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1045","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1045","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/2004.12200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102318256","display_name":"Menglong Xu","orcid":"https://orcid.org/0009-0006-0878-5502"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menglong Xu","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2498,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.9339323,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2547","last_page":"2551"},"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":0.9994000196456909,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/convolution","display_name":"Convolution (computer science)","score":0.8095349073410034},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7669873237609863},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7610749006271362},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.7076346278190613},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6631808280944824},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5544452667236328},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.5370053648948669},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5050175786018372},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4927568733692169},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.45710453391075134},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45381447672843933},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4123498797416687},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41123372316360474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4057607650756836},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3278195858001709},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21286779642105103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1665772795677185}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.8095349073410034},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669873237609863},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7610749006271362},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.7076346278190613},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6631808280944824},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5544452667236328},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.5370053648948669},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5050175786018372},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4927568733692169},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.45710453391075134},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45381447672843933},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4123498797416687},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41123372316360474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4057607650756836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3278195858001709},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21286779642105103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1665772795677185},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1045","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1045","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:2004.12200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.12200","pdf_url":"https://arxiv.org/pdf/2004.12200","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.12200","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.12200","pdf_url":"https://arxiv.org/pdf/2004.12200","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W114193738","https://openalex.org/W121281418","https://openalex.org/W1544266773","https://openalex.org/W2034940213","https://openalex.org/W2407023693","https://openalex.org/W2612445135","https://openalex.org/W2612800309","https://openalex.org/W2748659049","https://openalex.org/W2769912137","https://openalex.org/W2910655080","https://openalex.org/W2963163009","https://openalex.org/W2963414149","https://openalex.org/W2963420686","https://openalex.org/W2964187693","https://openalex.org/W2972792496","https://openalex.org/W2973226577","https://openalex.org/W4297775537","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W4286904253","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"One":[0],"difficult":[1],"problem":[2],"of":[3,37,39,77,80,93,104,127,152,157,159,181,186,188],"keyword":[4,30],"spotting":[5,31],"is":[6,191],"how":[7],"to":[8,24,27,41],"miniaturize":[9],"its":[10],"memory":[11],"footprint":[12],"while":[13],"maintain":[14],"a":[15,110,148,155,172,184,201],"high":[16],"precision.":[17],"Although":[18],"convolutional":[19],"neural":[20],"networks":[21],"have":[22],"shown":[23],"be":[25],"effective":[26],"the":[28,65,69,75,78,81,91,94,100,105,116,128,137,141,162,168,196],"small-footprint":[29],"problem,":[32],"they":[33],"still":[34],"need":[35],"hundreds":[36],"thousands":[38],"parameters":[40,79,158,187],"achieve":[42],"good":[43],"performance.":[44,143],"In":[45],"this":[46],"paper,":[47],"we":[48,63],"propose":[49],"an":[50,178],"efficient":[51],"model":[52,174,203],"based":[53],"on":[54,123],"depthwise":[55,70,95],"separable":[56,71,96],"convolution":[57,67,83,97,107],"layers":[58],"and":[59],"squeeze-and-excitation":[60,112],"blocks.":[61],"Specifically,":[62],"replace":[64],"standard":[66,82],"by":[68,98],"convolution,":[72],"which":[73,165,190],"reduces":[74],"number":[76,156,185],"without":[84],"significant":[85],"performance":[86,92],"degradation.":[87],"We":[88,114],"further":[89],"improve":[90],"reweighting":[99],"output":[101],"feature":[102],"maps":[103],"first":[106,163],"layer":[108],"with":[109,119,154,183],"so-called":[111],"block.":[113],"compared":[115],"proposed":[117,138],"method":[118,139,199],"five":[120],"representative":[121],"models":[122],"two":[124],"experimental":[125],"settings":[126],"Google":[129],"Speech":[130],"Commands":[131],"dataset.":[132],"Experimental":[133],"results":[134],"show":[135],"that":[136],"achieves":[140,147,177],"state-of-the-art":[142,197],"For":[144],"example,":[145],"it":[146],"classification":[149],"error":[150,179],"rate":[151,180],"3.29%":[153],"72K":[160],"in":[161],"experiment,":[164],"significantly":[166],"outperforms":[167],"comparison":[169,198],"methods":[170],"given":[171,200],"similar":[173,202],"size.":[175,204],"It":[176],"3.97%":[182],"10K,":[189],"also":[192],"slightly":[193],"better":[194],"than":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2020-05-01T00:00:00"}