{"id":"https://openalex.org/W4296069135","doi":"https://doi.org/10.21437/interspeech.2022-10558","title":"Exploring representation learning for small-footprint keyword spotting","display_name":"Exploring representation learning for small-footprint keyword spotting","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069135","doi":"https://doi.org/10.21437/interspeech.2022-10558"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10558","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10558","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2303.10912","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110945001","display_name":"Fan Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fan Cui","raw_affiliation_strings":["Xiaomi, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102707172","display_name":"Liyong Guo","orcid":"https://orcid.org/0009-0002-2465-3914"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liyong Guo","raw_affiliation_strings":["Xiaomi, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013004114","display_name":"Quandong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quandong Wang","raw_affiliation_strings":["Xiaomi, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362419","display_name":"Peng Gao","orcid":"https://orcid.org/0000-0003-4398-5471"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Xiaomi, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362598","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-0921-0122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5110945001"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2094,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42009858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3258","last_page":"3262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9976000189781189,"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":0.9954000115394592,"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/keyword-spotting","display_name":"Keyword spotting","score":0.8530383110046387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8204731941223145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6352036595344543},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.6007230281829834},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.558146595954895},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5235673785209656},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.49698904156684875},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.47644785046577454},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.45218297839164734},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4434789717197418},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4248940944671631},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.418876588344574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4122579097747803},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37187257409095764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3313557505607605}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8530383110046387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204731941223145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6352036595344543},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6007230281829834},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.558146595954895},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5235673785209656},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.49698904156684875},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.47644785046577454},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.45218297839164734},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4434789717197418},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4248940944671631},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.418876588344574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4122579097747803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37187257409095764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3313557505607605},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10558","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10558","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2303.10912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.10912","pdf_url":"https://arxiv.org/pdf/2303.10912","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2303.10912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.10912","pdf_url":"https://arxiv.org/pdf/2303.10912","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/W4296069135.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2034940213","https://openalex.org/W2507319753","https://openalex.org/W2507580616","https://openalex.org/W2510945575","https://openalex.org/W2748659049","https://openalex.org/W2769912137","https://openalex.org/W2797583228","https://openalex.org/W2888930363","https://openalex.org/W2889511491","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W2963628261","https://openalex.org/W2972792496","https://openalex.org/W2973049979","https://openalex.org/W2973226577","https://openalex.org/W3005680577","https://openalex.org/W3036601975","https://openalex.org/W3095949666","https://openalex.org/W3144247233","https://openalex.org/W3160799772","https://openalex.org/W4287592659","https://openalex.org/W4295312788","https://openalex.org/W4297808394","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,30],"investigate":[4],"representation":[5,32],"learning":[6,33,39],"for":[7,34,58],"low-resource":[8],"keyword":[9],"spotting":[10],"(KWS).":[11],"The":[12],"main":[13],"challenges":[14],"of":[15,134],"KWS":[16,35,87,103],"are":[17,51],"limited":[18,22],"labeled":[19,139],"data":[20],"and":[21,40,97,122],"available":[23],"device":[24],"resources.":[25],"To":[26],"address":[27],"those":[28],"challenges,":[29],"explore":[31],"by":[36,62],"self-supervised":[37,72,124],"contrastive":[38,47,65],"self-training":[41,119],"with":[42,108],"pretrained":[43,73,107],"model.":[44],"First,":[45],"local-global":[46,64],"siamese":[48],"networks":[49],"(LGCSiam)":[50],"designed":[52],"to":[53,84,89],"learn":[54,90],"similar":[55,59],"utterance-level":[56],"representations":[57],"audio":[60],"samplers":[61],"proposed":[63,101],"loss":[66],"without":[67],"requiring":[68],"ground-truth.":[69],"Second,":[70],"a":[71,80,137],"Wav2Vec":[74],"2.0":[75],"model":[76,88,104],"is":[77],"applied":[78],"as":[79],"constraint":[81],"module":[82,121,126],"(WVC)":[83],"force":[85],"the":[86,95,100,118,123,132],"frame-level":[91],"acoustic":[92],"representations.":[93],"By":[94],"LGCSiam":[96,125],"WVC":[98,120],"modules,":[99],"small-footprint":[102],"can":[105],"be":[106],"unlabeled":[109],"data.":[110],"Experiments":[111],"on":[112,136],"speech":[113],"commands":[114],"dataset":[115],"show":[116],"that":[117],"significantly":[127],"improve":[128],"accuracy,":[129],"especially":[130],"in":[131],"case":[133],"training":[135],"small":[138],"dataset.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}