{"id":"https://openalex.org/W3115583060","doi":"https://doi.org/10.1109/icpr48806.2021.9413191","title":"Resource-Efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization","display_name":"Resource-Efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3115583060","doi":"https://doi.org/10.1109/icpr48806.2021.9413191","mag":"3115583060"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9413191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/2012.10138","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017995708","display_name":"David Peter","orcid":"https://orcid.org/0000-0001-7950-9915"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"David Peter","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory Graz, University of Technology,Graz,Austria","Graz University of Technology,#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory Graz, University of Technology,Graz,Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Graz University of Technology,#TAB#","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019416885","display_name":"Wolfgang Roth","orcid":"https://orcid.org/0000-0002-0778-2418"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Wolfgang Roth","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory Graz, University of Technology,Graz,Austria","Graz University of Technology,#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory Graz, University of Technology,Graz,Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Graz University of Technology,#TAB#","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015798259","display_name":"Franz Pernkopf","orcid":"https://orcid.org/0000-0002-6356-3367"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Franz Pernkopf","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory Graz, University of Technology,Graz,Austria","Graz University of Technology,#TAB#"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory Graz, University of Technology,Graz,Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Graz University of Technology,#TAB#","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017995708"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01183874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1603 1025","issue":null,"first_page":"9273","last_page":"9279"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8141496181488037},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7989788055419922},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7172716856002808},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5894611477851868},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5754822492599487},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5707640647888184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49199697375297546},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47724390029907227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45657873153686523},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4067775011062622},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3339765667915344},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.208414226770401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141496181488037},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7989788055419922},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7172716856002808},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5894611477851868},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5754822492599487},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5707640647888184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49199697375297546},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47724390029907227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45657873153686523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4067775011062622},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3339765667915344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.208414226770401}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icpr48806.2021.9413191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2012.10138","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.10138","pdf_url":"https://arxiv.org/pdf/2012.10138","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3115583060","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2012.10138v1","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.2012.10138","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2012.10138","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:2012.10138","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2012.10138","pdf_url":"https://arxiv.org/pdf/2012.10138","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4399999976158142,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G5518976820","display_name":null,"funder_award_id":"I2706-N31","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G6783783255","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"}],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3115583060.pdf"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W2034940213","https://openalex.org/W2119717200","https://openalex.org/W2242818861","https://openalex.org/W2267635276","https://openalex.org/W2276486856","https://openalex.org/W2291160084","https://openalex.org/W2294282016","https://openalex.org/W2469490737","https://openalex.org/W2587529061","https://openalex.org/W2595614461","https://openalex.org/W2602634800","https://openalex.org/W2613332842","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2810075754","https://openalex.org/W2888429796","https://openalex.org/W2953219395","https://openalex.org/W2955425717","https://openalex.org/W2962746461","https://openalex.org/W2963163009","https://openalex.org/W2963473542","https://openalex.org/W2963778169","https://openalex.org/W2963821229","https://openalex.org/W2963918968","https://openalex.org/W2964081807","https://openalex.org/W2964259004","https://openalex.org/W2965658867","https://openalex.org/W2999963857","https://openalex.org/W3022571137","https://openalex.org/W3098773154","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6690026940","https://openalex.org/W6693397755","https://openalex.org/W6696798448","https://openalex.org/W6697189835","https://openalex.org/W6714171909","https://openalex.org/W6720242923","https://openalex.org/W6734868079","https://openalex.org/W6745614327","https://openalex.org/W6746451879","https://openalex.org/W6748057086","https://openalex.org/W6750665317","https://openalex.org/W6751831502","https://openalex.org/W6752515464","https://openalex.org/W6753701838","https://openalex.org/W6756887525","https://openalex.org/W6761209512","https://openalex.org/W6762718338","https://openalex.org/W6772849459","https://openalex.org/W6776525869"],"related_works":["https://openalex.org/W3134145319","https://openalex.org/W3169638910","https://openalex.org/W3082696729","https://openalex.org/W2904036992","https://openalex.org/W3098124779","https://openalex.org/W2534720278","https://openalex.org/W2996159591","https://openalex.org/W3105075025","https://openalex.org/W3159027058","https://openalex.org/W2905687271","https://openalex.org/W3178567251","https://openalex.org/W3006769269","https://openalex.org/W3003530529","https://openalex.org/W3091564954","https://openalex.org/W3190530808","https://openalex.org/W3198685759","https://openalex.org/W3118322613","https://openalex.org/W2781820017","https://openalex.org/W3097018422","https://openalex.org/W2793950911"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"neural":[3,34],"architecture":[4],"search":[5],"(NAS)":[6],"for":[7,14],"the":[8,30,39,44,66,88,114,130],"automatic":[9],"discovery":[10],"of":[11,32,46,74,116,137],"small":[12],"models":[13],"keyword":[15],"spotting":[16],"(KWS)":[17],"in":[18,110],"limited":[19],"resource":[20],"environments.":[21],"We":[22,93],"employ":[23],"a":[24,58],"differentiable":[25],"NAS":[26,51],"approach":[27],"to":[28,37,56,86,98,122,128,132],"optimize":[29],"structure":[31],"convolutional":[33],"networks":[35],"(CNNs)":[36],"maximize":[38],"classification":[40],"accuracy":[41,64,131],"while":[42],"minimizing":[43],"number":[45,115],"operations":[47],"per":[48],"inference.":[49],"Using":[50],"only,":[52],"we":[53,125],"were":[54,126],"able":[55,127],"obtain":[57],"highly":[59],"efficient":[60],"model":[61],"with":[62,71],"95.4%":[63],"on":[65],"Google":[67],"speech":[68],"commands":[69],"dataset":[70],"494.8":[72],"kB":[73,136],"memory":[75,89,138],"usage":[76,139],"and":[77,140],"19.6":[78],"million":[79,142],"operations.":[80,143],"Additionally,":[81],"weight":[82,96],"quantization":[83,97],"is":[84],"used":[85,106],"reduce":[87],"consumption":[90],"even":[91],"further.":[92],"show":[94],"that":[95],"low":[99],"bit-widths":[100],"(e.g.":[101],"1":[102],"bit)":[103],"can":[104],"be":[105],"without":[107],"substantial":[108],"loss":[109],"accuracy.":[111],"By":[112],"increasing":[113],"input":[117],"features":[118],"from":[119],"10":[120],"MFCC":[121,124],"20":[123],"increase":[129],"96.3%":[133],"at":[134],"340.1":[135],"27.1":[141]},"counts_by_year":[],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}