{"id":"https://openalex.org/W4372260355","doi":"https://doi.org/10.1109/icassp49357.2023.10096384","title":"Small-Footprint Slimmable Networks for Keyword Spotting","display_name":"Small-Footprint Slimmable Networks for Keyword Spotting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260355","doi":"https://doi.org/10.1109/icassp49357.2023.10096384"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5041416959","display_name":"Zuhaib Akhtar","orcid":"https://orcid.org/0000-0002-0338-6549"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zuhaib Akhtar","raw_affiliation_strings":["Amazon,Alexa Perceptual Technologies","Alexa Perceptual Technologies, Amazon","New York University, NY"],"affiliations":[{"raw_affiliation_string":"Amazon,Alexa Perceptual Technologies","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa Perceptual Technologies, Amazon","institution_ids":[]},{"raw_affiliation_string":"New York University, NY","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070084977","display_name":"Mohammad Omar Khursheed","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Omar Khursheed","raw_affiliation_strings":["Amazon,Alexa Perceptual Technologies","Alexa Perceptual Technologies, Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon,Alexa Perceptual Technologies","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa Perceptual Technologies, Amazon","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053619788","display_name":"D. Du","orcid":"https://orcid.org/0000-0002-4063-8805"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongsu Du","raw_affiliation_strings":["Amazon,Alexa Perceptual Technologies","Alexa Perceptual Technologies, Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon,Alexa Perceptual Technologies","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa Perceptual Technologies, Amazon","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000919546","display_name":"Yuzong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzong Liu","raw_affiliation_strings":["Amazon,Alexa Perceptual Technologies","Alexa Perceptual Technologies, Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon,Alexa Perceptual Technologies","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa Perceptual Technologies, Amazon","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041416959"],"corresponding_institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.8741,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77873836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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":0.9962000250816345,"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":0.859315037727356},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.8309290409088135},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8193318843841553},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.7274347543716431},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.7085435390472412},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6647689938545227},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6236573457717896},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5030176043510437},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.5026082992553711},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4966946244239807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48607996106147766},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47868233919143677},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4209071099758148},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4110746383666992}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.859315037727356},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.8309290409088135},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8193318843841553},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.7274347543716431},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.7085435390472412},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6647689938545227},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6236573457717896},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5030176043510437},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5026082992553711},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4966946244239807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48607996106147766},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47868233919143677},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4209071099758148},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4110746383666992},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2405666970","https://openalex.org/W2407023693","https://openalex.org/W2507319753","https://openalex.org/W2748659049","https://openalex.org/W2797583228","https://openalex.org/W2885311373","https://openalex.org/W2905741102","https://openalex.org/W2947681860","https://openalex.org/W2950014519","https://openalex.org/W2953384591","https://openalex.org/W2962935523","https://openalex.org/W2981698279","https://openalex.org/W2994749257","https://openalex.org/W3121327306","https://openalex.org/W3162309234","https://openalex.org/W3198035615","https://openalex.org/W3204647170","https://openalex.org/W3207326706","https://openalex.org/W4224821750","https://openalex.org/W4226020322","https://openalex.org/W4385245566","https://openalex.org/W6713134421","https://openalex.org/W6739901393","https://openalex.org/W6745447533","https://openalex.org/W6750665317","https://openalex.org/W6753278433","https://openalex.org/W6757036269","https://openalex.org/W6763381322","https://openalex.org/W6767064347","https://openalex.org/W6789284983","https://openalex.org/W6790299800"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"present":[4],"Slimmable":[5,92],"Neural":[6,29],"Networks":[7,30],"applied":[8],"to":[9,24,71,108],"the":[10,44,65,104],"problem":[11],"of":[12,36,46,99],"small-footprint":[13],"keyword":[14],"spotting.":[15],"We":[16,42,76],"show":[17,77],"that":[18,78],"slimmable":[19,79],"neural":[20,93],"networks":[21,94],"allow":[22],"us":[23],"create":[25],"super-nets":[26],"from":[27,33,90],"Convolutional":[28],"and":[31,54,58,114],"Transformers,":[32],"which":[34],"sub-networks":[35],"different":[37,112,118],"sizes":[38],"can":[39,81],"be":[40,109],"extracted.":[41],"demonstrate":[43],"usefulness":[45],"these":[47],"models":[48,63,80,88,100],"on":[49,62],"in-house":[50],"voice":[51],"assistant":[52],"data":[53],"Google":[55],"Speech":[56],"Commands,":[57],"focus":[59],"our":[60],"efforts":[61],"for":[64],"on-device":[66],"use":[67],"case,":[68],"limiting":[69],"ourselves":[70],"less":[72],"than":[73],"250k":[74],"parameters.":[75],"match":[82],"(and":[83],"in":[84],"some":[85],"cases,":[86],"outperform)":[87],"trained":[89],"scratch.":[91],"are":[95],"therefore":[96],"a":[97],"class":[98],"particularly":[101],"useful":[102],"when":[103],"same":[105],"functionality":[106],"is":[107],"replicated":[110],"at":[111],"memory":[113],"compute":[115],"budgets,":[116],"with":[117],"accuracy":[119],"requirements.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}