{"id":"https://openalex.org/W3154934206","doi":"https://doi.org/10.1109/icassp43922.2022.9746535","title":"End-to-End Keyword Spotting Using Neural Architecture Search and Quantization","display_name":"End-to-End Keyword Spotting Using Neural Architecture Search and Quantization","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3154934206","doi":"https://doi.org/10.1109/icassp43922.2022.9746535","mag":"3154934206"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746535","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/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":["Graz University of Technology,Signal Processing and Speech Communication Laboratory,Graz,Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology,Signal Processing and Speech Communication Laboratory,Graz,Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","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":["Graz University of Technology,Signal Processing and Speech Communication Laboratory,Graz,Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology,Signal Processing and Speech Communication Laboratory,Graz,Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","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":["Graz University of Technology,Signal Processing and Speech Communication Laboratory,Graz,Austria","Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology,Signal Processing and Speech Communication Laboratory,Graz,Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","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":1.4642,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83510892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3423","last_page":"3427"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9995999932289124,"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":0.7806580662727356},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.7756866216659546},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.7016294002532959},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6573019623756409},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.568162202835083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5398830771446228},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5344393253326416},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5273828506469727},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45445749163627625},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.42712461948394775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42680004239082336},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41867974400520325},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29206085205078125},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.22165408730506897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806580662727356},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7756866216659546},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.7016294002532959},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6573019623756409},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.568162202835083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5398830771446228},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5344393253326416},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5273828506469727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45445749163627625},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.42712461948394775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42680004239082336},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41867974400520325},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29206085205078125},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.22165408730506897},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746535","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1583776211","https://openalex.org/W2034940213","https://openalex.org/W2242818861","https://openalex.org/W2276486856","https://openalex.org/W2294282016","https://openalex.org/W2407023693","https://openalex.org/W2587529061","https://openalex.org/W2595614461","https://openalex.org/W2602634800","https://openalex.org/W2613332842","https://openalex.org/W2765347007","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2810075754","https://openalex.org/W2916954108","https://openalex.org/W2947565354","https://openalex.org/W2947591755","https://openalex.org/W2951104886","https://openalex.org/W2953219395","https://openalex.org/W2962746461","https://openalex.org/W2962824709","https://openalex.org/W2963163009","https://openalex.org/W2963778169","https://openalex.org/W2963918968","https://openalex.org/W2964052309","https://openalex.org/W2964259004","https://openalex.org/W2982182345","https://openalex.org/W2994840239","https://openalex.org/W2995738369","https://openalex.org/W3001133453","https://openalex.org/W3015287265","https://openalex.org/W3022571137","https://openalex.org/W3028019732","https://openalex.org/W3037455673","https://openalex.org/W3082696729","https://openalex.org/W3084006547","https://openalex.org/W3094136258","https://openalex.org/W3098773154","https://openalex.org/W3134145319","https://openalex.org/W3160521245","https://openalex.org/W4288413318","https://openalex.org/W4295262505","https://openalex.org/W4300687381","https://openalex.org/W6690026940","https://openalex.org/W6693397755","https://openalex.org/W6745159674","https://openalex.org/W6745614327","https://openalex.org/W6746451879","https://openalex.org/W6748057086","https://openalex.org/W6750665317","https://openalex.org/W6752515464","https://openalex.org/W6753968785","https://openalex.org/W6756887525","https://openalex.org/W6760069825","https://openalex.org/W6763198355","https://openalex.org/W6763341371","https://openalex.org/W6767597771","https://openalex.org/W6769963626","https://openalex.org/W6771595542","https://openalex.org/W6776525869","https://openalex.org/W6782926259","https://openalex.org/W6784581357","https://openalex.org/W6787768724","https://openalex.org/W6843142645"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W3119978414","https://openalex.org/W2114097550","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W2000885660","https://openalex.org/W1969408022","https://openalex.org/W2117995638","https://openalex.org/W1989658893","https://openalex.org/W2545741539"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"neural":[3,33],"architecture":[4],"search":[5],"(NAS)":[6],"for":[7,17],"the":[8,29,59,67,124],"automatic":[9],"discovery":[10],"of":[11,31,53,112,131],"end-to-end":[12,77],"keyword":[13],"spotting":[14],"(KWS)":[15],"models":[16,78],"limited":[18],"resource":[19],"environments.":[20],"We":[21,62],"employ":[22],"a":[23,42,105,128],"differentiable":[24],"NAS":[25,98],"approach":[26],"to":[27,57,79,103],"optimize":[28],"structure":[30],"convolutional":[32],"networks":[34],"(CNNs)":[35],"operating":[36],"on":[37,66,135],"raw":[38],"audio":[39],"waveforms.":[40],"After":[41],"suitable":[43],"KWS":[44],"model":[45,108,126],"is":[46],"found":[47],"with":[48,109],"NAS,":[49],"we":[50,74,88,100],"conduct":[51,63],"quantization":[52,92],"weights":[54],"and":[55,93,117,142],"activations":[56],"reduce":[58],"memory":[60],"footprint.":[61],"extensive":[64],"experiments":[65],"Google":[68],"speech":[69],"commands":[70],"dataset.":[71],"In":[72],"particular,":[73],"compare":[75,89],"our":[76],"mel-frequency":[80],"cepstral":[81],"coefficient":[82],"(MFCC)":[83],"based":[84],"CNNs.":[85],"For":[86],"quantization,":[87,123],"fixed":[90],"bit-width":[91,95,122],"trained":[94,121],"quantization.":[96],"Using":[97,120],"only,":[99],"were":[101],"able":[102],"obtain":[104],"highly":[106],"efficient":[107],"an":[110],"accuracy":[111,130],"95.55%":[113],"using":[114,134],"75.7k":[115],"parameters":[116],"13.6M":[118],"operations.":[119],"same":[125],"achieves":[127],"test":[129],"93.76%":[132],"while":[133],"average":[136],"only":[137],"2.91":[138],"bits":[139,144],"per":[140,145],"activation":[141],"2.51":[143],"weight.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}