{"id":"https://openalex.org/W3160521245","doi":"https://doi.org/10.1109/icassp39728.2021.9414848","title":"AutoKWS: Keyword Spotting with Differentiable Architecture Search","display_name":"AutoKWS: Keyword Spotting with Differentiable Architecture Search","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160521245","doi":"https://doi.org/10.1109/icassp39728.2021.9414848","mag":"3160521245"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100335322","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0002-7937-0826"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bo Zhang","raw_affiliation_strings":["Xiaomi AI Lab"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333961","display_name":"Wenfeng Li","orcid":"https://orcid.org/0000-0001-9491-6543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenfeng Li","raw_affiliation_strings":["Xiaomi AI Lab"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691413","display_name":"Qingyuan Li","orcid":"https://orcid.org/0000-0001-9871-7576"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyuan Li","raw_affiliation_strings":["Xiaomi AI Lab"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113987256","display_name":"Weiji Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiji Zhuang","raw_affiliation_strings":["Xiaomi AI Lab"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512474","display_name":"Xiangxiang Chu","orcid":"https://orcid.org/0000-0003-2548-0605"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangxiang Chu","raw_affiliation_strings":["Xiaomi AI Lab"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi AI Lab"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100335322"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5043,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93509128,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2830","last_page":"2834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":0.9998999834060669,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8635901212692261},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7127918601036072},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6987150311470032},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5880387425422668},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5467438101768494},{"id":"https://openalex.org/keywords/expansive","display_name":"Expansive","score":0.5403857827186584},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5386530756950378},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48607566952705383},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.47619450092315674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46283817291259766},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4066774249076843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.347541868686676},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.34497445821762085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3300921320915222},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2557925283908844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8635901212692261},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7127918601036072},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6987150311470032},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5880387425422668},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5467438101768494},{"id":"https://openalex.org/C2780502288","wikidata":"https://www.wikidata.org/wiki/Q28838156","display_name":"Expansive","level":3,"score":0.5403857827186584},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5386530756950378},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48607566952705383},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.47619450092315674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46283817291259766},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4066774249076843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.347541868686676},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34497445821762085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3300921320915222},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2557925283908844},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C30407753","wikidata":"https://www.wikidata.org/wiki/Q186191","display_name":"Compressive strength","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1496120315","https://openalex.org/W1522301498","https://openalex.org/W2034940213","https://openalex.org/W2171019095","https://openalex.org/W2194775991","https://openalex.org/W2407023693","https://openalex.org/W2510945575","https://openalex.org/W2752782242","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2797759721","https://openalex.org/W2810075754","https://openalex.org/W2930364467","https://openalex.org/W2936774411","https://openalex.org/W2951104886","https://openalex.org/W2953604046","https://openalex.org/W2962707338","https://openalex.org/W2963977978","https://openalex.org/W2964121744","https://openalex.org/W2964187693","https://openalex.org/W2972482531","https://openalex.org/W2973226577","https://openalex.org/W3007947150","https://openalex.org/W3015205859","https://openalex.org/W3015287265","https://openalex.org/W3021181539","https://openalex.org/W3021905974","https://openalex.org/W3024022091","https://openalex.org/W3025581723","https://openalex.org/W3082696729","https://openalex.org/W3095175338","https://openalex.org/W3095653574","https://openalex.org/W3096025930","https://openalex.org/W3107893198","https://openalex.org/W3203915045","https://openalex.org/W6631190155","https://openalex.org/W6714171909","https://openalex.org/W6746451879","https://openalex.org/W6750665317","https://openalex.org/W6752515464","https://openalex.org/W6765297142","https://openalex.org/W6776542421"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4385352507","https://openalex.org/W4389912005","https://openalex.org/W4286904253","https://openalex.org/W2386245264","https://openalex.org/W1966806973","https://openalex.org/W2124014456","https://openalex.org/W2034940213"],"abstract_inverted_index":{"Smart":[0],"audio":[1],"devices":[2],"are":[3,55],"gated":[4],"by":[5],"an":[6,70,74],"always-on":[7],"lightweight":[8],"keyword":[9],"spotting":[10],"program":[11],"to":[12,20,41,83,92],"reduce":[13],"power":[14],"consumption.":[15],"It":[16],"is":[17],"however":[18],"challenging":[19],"design":[21],"models":[22],"that":[23],"have":[24,38],"both":[25],"high":[26],"accuracy":[27,103],"and":[28,33,53],"low":[29],"latency":[30],"for":[31],"accurate":[32],"fast":[34],"responsiveness.":[35],"Many":[36],"efforts":[37],"been":[39],"made":[40],"develop":[42],"end-to-end":[43],"neural":[44,89],"networks,":[45],"in":[46,73,87],"which":[47],"depthwise":[48],"separable":[49],"convolutions,":[50,52],"temporal":[51],"LSTMs":[54],"adopted":[56],"as":[57],"building":[58],"units.":[59],"Nonetheless,":[60],"these":[61],"networks":[62],"designed":[63],"with":[64,110],"human":[65],"expertise":[66],"may":[67],"not":[68],"achieve":[69],"optimal":[71],"trade-off":[72],"expansive":[75],"search":[76,91],"space.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81],"propose":[82],"leverage":[84],"recent":[85],"advances":[86],"differentiable":[88],"architecture":[90],"discover":[93],"more":[94],"efficient":[95],"networks.":[96],"Our":[97],"searched":[98],"model":[99],"attains":[100],"97.2%":[101],"top-1":[102],"on":[104],"Google":[105],"Speech":[106],"Command":[107],"Dataset":[108],"v1":[109],"only":[111],"nearly":[112],"100K":[113],"parameters.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4}],"updated_date":"2026-02-18T06:20:13.636215","created_date":"2025-10-10T00:00:00"}