{"id":"https://openalex.org/W4385485026","doi":"https://doi.org/10.1109/icasspw59220.2023.10193371","title":"Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining","display_name":"Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385485026","doi":"https://doi.org/10.1109/icasspw59220.2023.10193371"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.01703.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055991258","display_name":"Holger Severin Bovbjerg","orcid":"https://orcid.org/0000-0002-8735-739X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Holger Severin Bovbjerg","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Aalborg University,Department of Electronic Systems,Denmark","Department of Electronic Systems, Aalborg University, Denmark","Pioneer Centre for AI, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Department of Electronic Systems,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Pioneer Centre for AI, Denmark","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.8892940282821655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8280471563339233},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6011127829551697},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5997095108032227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5696392059326172},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5354034900665283},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4879540801048279},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4822148084640503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4614158570766449},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4387018382549286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.434481680393219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3471415042877197},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09368535876274109}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8892940282821655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280471563339233},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6011127829551697},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5997095108032227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5696392059326172},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5354034900665283},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4879540801048279},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4822148084640503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4614158570766449},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4387018382549286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.434481680393219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3471415042877197},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09368535876274109},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/59e577a0-23d1-4e71-850c-a00f557f15f8","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/59e577a0-23d1-4e71-850c-a00f557f15f8","pdf_url":"https://arxiv.org/pdf/2210.01703.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bovbjerg, H S & Tan, Z H 2023, Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining. in ICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings., 10193371, IEEE (Institute of Electrical and Electronics Engineers), 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023, Rhodes Island, Greece, 04/06/2023. https://doi.org/10.1109/ICASSPW59220.2023.10193371","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/59e577a0-23d1-4e71-850c-a00f557f15f8","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/59e577a0-23d1-4e71-850c-a00f557f15f8","pdf_url":"https://arxiv.org/pdf/2210.01703.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bovbjerg, H S & Tan, Z H 2023, Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining. in ICASSPW 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, Proceedings., 10193371, IEEE (Institute of Electrical and Electronics Engineers), 2023 IEEE International Conference on Acoustics, Speech and Signal Processing Workshops, ICASSPW 2023, Rhodes Island, Greece, 04/06/2023. https://doi.org/10.1109/ICASSPW59220.2023.10193371","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385485026.pdf","grobid_xml":"https://content.openalex.org/works/W4385485026.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W2768282280","https://openalex.org/W2797583228","https://openalex.org/W2936774411","https://openalex.org/W2973049979","https://openalex.org/W2995181338","https://openalex.org/W3036601975","https://openalex.org/W3094502228","https://openalex.org/W3100859887","https://openalex.org/W3121052760","https://openalex.org/W3148040514","https://openalex.org/W3175359298","https://openalex.org/W3193078976","https://openalex.org/W3197580070","https://openalex.org/W3198035615","https://openalex.org/W3209984917","https://openalex.org/W4206567542","https://openalex.org/W4221145109","https://openalex.org/W4300900294","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6743178762","https://openalex.org/W6746052068","https://openalex.org/W6750665317","https://openalex.org/W6777232839","https://openalex.org/W6779977557","https://openalex.org/W6780218876","https://openalex.org/W6784333009","https://openalex.org/W6788280241","https://openalex.org/W6797980327","https://openalex.org/W6799910520","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W4408353962","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539"],"abstract_inverted_index":{"Keyword":[0],"Spotting":[1],"(KWS)":[2],"models":[3,19,74,87,101,113],"are":[4,75],"becoming":[5],"increasingly":[6],"integrated":[7],"into":[8],"various":[9],"systems,":[10],"e.g.":[11],"voice":[12],"assistants.":[13],"To":[14],"achieve":[15],"satisfactory":[16],"performance,":[17],"these":[18],"typically":[20],"rely":[21],"on":[22,85,119],"a":[23,47,120,138],"large":[24,64],"amount":[25],"of":[26,83,98,123,149],"labelled":[27,103],"data,":[28],"limiting":[29],"their":[30],"applications":[31],"only":[32],"to":[33,137,151],"situations":[34],"where":[35],"such":[36,46],"data":[37,104,128],"is":[38,68,105,131],"available.":[39],"Self-supervised":[40],"Learning":[41],"(SSL)":[42],"methods":[43,56],"can":[44,94],"mitigate":[45],"reliance":[48],"by":[49],"leveraging":[50],"readily-available":[51],"unlabelled":[52],"data.":[53],"Most":[54],"SSL":[55,84,93],"for":[57,63,88],"speech":[58],"have":[59],"primarily":[60],"been":[61],"studied":[62],"models,":[65],"whereas":[66],"this":[67],"not":[69],"ideal,":[70],"as":[71],"compact":[72,110],"KWS":[73,89,100,112],"generally":[76],"required.":[77],"This":[78],"paper":[79],"explores":[80],"the":[81,96,124],"effectiveness":[82],"small":[86,99],"and":[90,116],"establishes":[91],"that":[92,133],"enhance":[95],"performance":[97],"when":[102],"scarce.":[106],"We":[107],"pretrain":[108],"three":[109],"transformer-based":[111],"using":[114],"Data2Vec,":[115],"fine-tune":[117],"them":[118],"label-deficient":[121,144],"setup":[122],"Google":[125],"Speech":[126],"Commands":[127],"set.":[129],"It":[130],"found":[132],"Data2Vec":[134],"pretraining":[135],"leads":[136],"significant":[139],"increase":[140],"in":[141],"accuracy,":[142],"with":[143],"scenarios":[145],"showing":[146],"an":[147],"improvement":[148],"8.22%":[150],"11.18%":[152],"absolute":[153],"accuracy.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}