{"id":"https://openalex.org/W2984988529","doi":"https://doi.org/10.1109/icassp40776.2020.9053395","title":"Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutions","display_name":"Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutions","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2984988529","doi":"https://doi.org/10.1109/icassp40776.2020.9053395","mag":"2984988529"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/1911.02086","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083476012","display_name":"Simon Mittermaier","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Simon Mittermaier","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Technische Universit\u00e3t M\u00fcnchen Munich, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technische Universit\u00e3t M\u00fcnchen Munich, Germany#TAB#","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079663771","display_name":"Ludwig K\u00fcrzinger","orcid":"https://orcid.org/0000-0001-5312-3870"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ludwig Kurzinger","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Technische Universit\u00e3t M\u00fcnchen Munich, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technische Universit\u00e3t M\u00fcnchen Munich, Germany#TAB#","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067647232","display_name":"Bernd Waschneck","orcid":"https://orcid.org/0000-0003-0294-8594"},"institutions":[{"id":"https://openalex.org/I137594350","display_name":"Infineon Technologies (Germany)","ror":"https://ror.org/005kw6t15","country_code":"DE","type":"company","lineage":["https://openalex.org/I137594350"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Waschneck","raw_affiliation_strings":["Infineon Technologies AG, Munich & Dresden, Germany","[Infineon Technologies AG, Munich & Dresden, Germany]"],"affiliations":[{"raw_affiliation_string":"Infineon Technologies AG, Munich & Dresden, Germany","institution_ids":["https://openalex.org/I137594350"]},{"raw_affiliation_string":"[Infineon Technologies AG, Munich & Dresden, Germany]","institution_ids":["https://openalex.org/I137594350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Rigoll","raw_affiliation_strings":["Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","Technische Universit\u00e3t M\u00fcnchen Munich, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technische Universit\u00e3t M\u00fcnchen Munich, Germany#TAB#","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083476012"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.39056468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7454","last_page":"7458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music 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":0.9991999864578247,"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/keyword-spotting","display_name":"Keyword spotting","score":0.8661830425262451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8439862728118896},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.7714015245437622},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5728583335876465},{"id":"https://openalex.org/keywords/sinc-function","display_name":"Sinc function","score":0.5612638592720032},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5232968926429749},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45853763818740845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35823795199394226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35505521297454834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3269071578979492},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09856665134429932}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8661830425262451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439862728118896},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.7714015245437622},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5728583335876465},{"id":"https://openalex.org/C152303783","wikidata":"https://www.wikidata.org/wiki/Q855949","display_name":"Sinc function","level":2,"score":0.5612638592720032},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5232968926429749},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45853763818740845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35823795199394226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35505521297454834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3269071578979492},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09856665134429932},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053395","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1911.02086","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.02086","pdf_url":"https://arxiv.org/pdf/1911.02086","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"},{"id":"mag:2984988529","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.02086.pdf","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.1911.02086","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.02086","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"},{"id":"doi:10.17023/6zmd-gy28","is_oa":true,"landing_page_url":"https://doi.org/10.17023/6zmd-gy28","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"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:1911.02086","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.02086","pdf_url":"https://arxiv.org/pdf/1911.02086","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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2984988529.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1553469512","https://openalex.org/W1836465849","https://openalex.org/W1936750108","https://openalex.org/W1999085092","https://openalex.org/W2034940213","https://openalex.org/W2163605009","https://openalex.org/W2442974303","https://openalex.org/W2531409750","https://openalex.org/W2604319603","https://openalex.org/W2612445135","https://openalex.org/W2625477277","https://openalex.org/W2769912137","https://openalex.org/W2787752687","https://openalex.org/W2797583228","https://openalex.org/W2901616798","https://openalex.org/W2904036992","https://openalex.org/W2906043559","https://openalex.org/W2962901777","https://openalex.org/W2963071736","https://openalex.org/W2963125010","https://openalex.org/W2964052309","https://openalex.org/W2964121744","https://openalex.org/W2964187693","https://openalex.org/W2973226577","https://openalex.org/W6638667902","https://openalex.org/W6684191040","https://openalex.org/W6737664043","https://openalex.org/W6746451879","https://openalex.org/W6750665317","https://openalex.org/W6756859573","https://openalex.org/W6765069029"],"related_works":["https://openalex.org/W3015287265","https://openalex.org/W3037988796","https://openalex.org/W3094362447","https://openalex.org/W2939412000","https://openalex.org/W2982537484","https://openalex.org/W2960506825","https://openalex.org/W3025284828","https://openalex.org/W3089355420","https://openalex.org/W3003492753","https://openalex.org/W3083587321","https://openalex.org/W2913838064","https://openalex.org/W3177895698","https://openalex.org/W2900627270","https://openalex.org/W3163777876","https://openalex.org/W3020078379","https://openalex.org/W3089317739","https://openalex.org/W2522346295","https://openalex.org/W2908443740","https://openalex.org/W3204626765","https://openalex.org/W3036607966"],"abstract_inverted_index":{"Keyword":[0],"Spotting":[1],"(KWS)":[2],"enables":[3],"speech-based":[4],"user":[5],"interaction":[6],"on":[7,20,121],"smart":[8,16],"devices.":[9],"Always-on":[10],"and":[11,23,42,56,69,79],"battery-powered":[12],"application":[13],"scenarios":[14],"for":[15],"devices":[17],"put":[18],"constraints":[19],"hardware":[21],"resources":[22],"power":[24,68],"consumption,":[25],"while":[26],"also":[27],"demanding":[28],"high":[29],"accuracy":[30,118],"as":[31,33],"well":[32],"real-time":[34],"capability.":[35],"Previous":[36],"architectures":[37],"first":[38],"extracted":[39],"acoustic":[40],"features":[41,98],"then":[43],"applied":[44],"a":[45],"neural":[46],"network":[47,114],"to":[48,59,66],"classify":[49],"keyword":[50],"probabilities,":[51],"optimizing":[52],"towards":[53],"memory":[54,70,103],"footprint":[55,104],"execution":[57],"time.Compared":[58],"previous":[60],"publications,":[61],"we":[62],"took":[63],"additional":[64],"steps":[65,82],"reduce":[67],"consumption":[71],"without":[72],"reducing":[73],"classification":[74],"accuracy.":[75],"Power-consuming":[76],"audio":[77],"preprocessing":[78],"data":[80],"transfer":[81],"are":[83],"eliminated":[84],"by":[85,108],"directly":[86],"classifying":[87],"from":[88],"raw":[89],"audio.":[90],"For":[91],"this,":[92],"our":[93],"end-to-end":[94],"architecture":[95],"extracts":[96],"spectral":[97],"using":[99],"parametrized":[100],"Sinc-convolutions.":[101],"Its":[102],"is":[105],"further":[106],"reduced":[107],"grouping":[109],"depthwise":[110],"separable":[111],"convolutions.":[112],"Our":[113],"achieves":[115],"the":[116],"competitive":[117],"of":[119],"96.4%":[120],"Google's":[122],"Speech":[123],"Commands":[124],"test":[125],"set":[126],"with":[127],"only":[128],"62k":[129],"parameters.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}