{"id":"https://openalex.org/W3095939318","doi":"https://doi.org/10.1109/icassp39728.2021.9413564","title":"Small Footprint Text-Independent Speaker Verification For Embedded Systems","display_name":"Small Footprint Text-Independent Speaker Verification For Embedded Systems","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3095939318","doi":"https://doi.org/10.1109/icassp39728.2021.9413564","mag":"3095939318"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413564","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.01709","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026773294","display_name":"Julien Balian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julien Balian","raw_affiliation_strings":["Sonos Inc., Paris, France","Sonos Inc.,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sonos Inc., Paris, France","institution_ids":[]},{"raw_affiliation_string":"Sonos Inc.,Paris,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090996481","display_name":"Raffaele Tavarone","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raffaele Tavarone","raw_affiliation_strings":["Sonos Inc., Paris, France","Sonos Inc.,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sonos Inc., Paris, France","institution_ids":[]},{"raw_affiliation_string":"Sonos Inc.,Paris,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010686846","display_name":"Mathieu Poumeyrol","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathieu Poumeyrol","raw_affiliation_strings":["Sonos Inc., Paris, France","Sonos Inc.,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sonos Inc., Paris, France","institution_ids":[]},{"raw_affiliation_string":"Sonos Inc.,Paris,France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029064712","display_name":"Alice Coucke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alice Coucke","raw_affiliation_strings":["Sonos Inc., Paris, France","Sonos Inc.,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sonos Inc., Paris, France","institution_ids":[]},{"raw_affiliation_string":"Sonos Inc.,Paris,France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1399,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51506748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6179","last_page":"6183"},"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":0.9998000264167786,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7683957815170288},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.736788809299469},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6766499280929565},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6015595197677612},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.562411904335022},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5475645065307617},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5361195802688599},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5132974982261658},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5106714367866516},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4697098135948181},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45867404341697693},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4365425109863281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3710687756538391},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3238723874092102},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08319470286369324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7683957815170288},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.736788809299469},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6766499280929565},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6015595197677612},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.562411904335022},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5475645065307617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5361195802688599},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5132974982261658},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5106714367866516},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4697098135948181},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45867404341697693},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4365425109863281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3710687756538391},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3238723874092102},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08319470286369324},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/icassp39728.2021.9413564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413564","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"},{"id":"pmh:oai:arXiv.org:2011.01709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01709","pdf_url":"https://arxiv.org/pdf/2011.01709","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:3095939318","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.01709.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.2011.01709","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.01709","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-journal"},{"id":"doi:10.17023/dyex-9n05","is_oa":true,"landing_page_url":"https://doi.org/10.17023/dyex-9n05","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:2011.01709","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.01709","pdf_url":"https://arxiv.org/pdf/2011.01709","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095939318.pdf","grobid_xml":"https://content.openalex.org/works/W3095939318.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2114925438","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2587150483","https://openalex.org/W2748488820","https://openalex.org/W2763188033","https://openalex.org/W2794506738","https://openalex.org/W2796485741","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2916024349","https://openalex.org/W2916104401","https://openalex.org/W2937776600","https://openalex.org/W2960935792","https://openalex.org/W2962788625","https://openalex.org/W2963040451","https://openalex.org/W2963351448","https://openalex.org/W2963460857","https://openalex.org/W2963628261","https://openalex.org/W2969985801","https://openalex.org/W2972609576","https://openalex.org/W2981461916","https://openalex.org/W3013020904","https://openalex.org/W3015261361","https://openalex.org/W3015537910","https://openalex.org/W6688816777","https://openalex.org/W6735531217","https://openalex.org/W6745415975","https://openalex.org/W6749813370","https://openalex.org/W6760112457","https://openalex.org/W6765488738","https://openalex.org/W6769178842","https://openalex.org/W6775243439"],"related_works":["https://openalex.org/W3163082428","https://openalex.org/W2972871438","https://openalex.org/W2951630015","https://openalex.org/W3178353629","https://openalex.org/W2311760409","https://openalex.org/W3048043966","https://openalex.org/W2972986505","https://openalex.org/W2960935792","https://openalex.org/W2970827607","https://openalex.org/W2140335396","https://openalex.org/W2952098737","https://openalex.org/W2972924883","https://openalex.org/W2910779830","https://openalex.org/W2767741204","https://openalex.org/W3081044928","https://openalex.org/W2946615417","https://openalex.org/W3211614993","https://openalex.org/W3142516134","https://openalex.org/W1585307611","https://openalex.org/W2900161882"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"approaches":[3],"to":[4,118],"speaker":[5],"verification":[6,59],"have":[7],"proven":[8],"successful,":[9],"but":[10],"typical":[11,73],"computational":[12],"requirements":[13],"of":[14,34,48,66,74,112,123,134,140],"State-Of-The-Art":[15],"(SOTA)":[16],"systems":[17,76],"make":[18],"them":[19],"unsuited":[20],"for":[21],"embedded":[22],"applications.":[23],"In":[24],"this":[25],"work,":[26],"we":[27,95],"present":[28],"a":[29,45,84,90,107,128,132],"two-stage":[30],"model":[31,98,122],"architecture":[32],"orders":[33],"magnitude":[35],"smaller":[36,86],"than":[37,87],"common":[38],"solutions":[39],"(237.5K":[40],"learning":[41,141],"parameters,":[42],"11.5MFLOPS)":[43],"reaching":[44],"competitive":[46],"result":[47],"3.31%":[49],"Equal":[50],"Error":[51],"Rate":[52],"(EER)":[53],"on":[54,70,89,99],"the":[55,64,79,100,119,124,138],"well":[56],"established":[57],"VoxCeleb1":[58],"test":[60],"set.":[61],"We":[62,105],"demonstrate":[63],"possibility":[65],"running":[67],"our":[68,97],"solution":[69],"small":[71],"devices":[72],"IoT":[75],"such":[77],"as":[78],"Raspberry":[80],"Pi":[81],"3B":[82],"with":[83,116],"latency":[85],"200ms":[88],"5s":[91],"long":[92],"utterance.":[93],"Additionally,":[94],"evaluate":[96],"acoustically":[101],"challenging":[102],"VOiCES":[103,126],"corpus.":[104],"report":[106],"limited":[108],"increase":[109],"in":[110,137],"EER":[111],"2.6":[113],"percentage":[114],"points":[115],"respect":[117],"best":[120],"scoring":[121],"2019":[125],"from":[127],"Distance":[129],"Challenge,":[130],"against":[131],"reduction":[133],"25.6":[135],"times":[136],"number":[139],"parameters.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}