{"id":"https://openalex.org/W4375868863","doi":"https://doi.org/10.1109/icassp49357.2023.10095929","title":"Self-Supervised Speech Representation Learning for Keyword-Spotting With Light-Weight Transformers","display_name":"Self-Supervised Speech Representation Learning for Keyword-Spotting With Light-Weight Transformers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868863","doi":"https://doi.org/10.1109/icassp49357.2023.10095929"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101425533","display_name":"Chenyang Gao","orcid":"https://orcid.org/0000-0002-0280-7882"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chenyang Gao","raw_affiliation_strings":["The State University of New Jersey,Rutgers","Rutgers, The State University of New Jersey"],"affiliations":[{"raw_affiliation_string":"The State University of New Jersey,Rutgers","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Rutgers, The State University of New Jersey","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050492878","display_name":"Yue Gu","orcid":"https://orcid.org/0000-0002-6402-2386"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Gu","raw_affiliation_strings":["Amazon,Alexa Perceptual Technologies","Alexa Perceptual Technologies, Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon,Alexa Perceptual Technologies","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa Perceptual Technologies, Amazon","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014387832","display_name":"Francesco Caliv\u00e1","orcid":"https://orcid.org/0000-0002-0425-7511"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Francesco Caliva","raw_affiliation_strings":["Amazon,Alexa Perceptual Technologies","Alexa Perceptual Technologies, Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon,Alexa Perceptual Technologies","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa Perceptual Technologies, Amazon","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000919546","display_name":"Yuzong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzong Liu","raw_affiliation_strings":["Amazon,Alexa Perceptual Technologies","Alexa Perceptual Technologies, Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon,Alexa Perceptual Technologies","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Alexa Perceptual Technologies, Amazon","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101425533"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":1.049,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80555306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/T10028","display_name":"Topic Modeling","score":0.9966999888420105,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965000152587891,"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":0.9031861424446106},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8147462606430054},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6792285442352295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6159772872924805},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5720131397247314},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5671229958534241},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.5340463519096375},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.5159895420074463},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5038010478019714},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5036093592643738},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5016646385192871},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.49239885807037354},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4837243854999542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3783763349056244},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.34477150440216064},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12654855847358704}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9031861424446106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8147462606430054},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6792285442352295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6159772872924805},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5720131397247314},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5671229958534241},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.5340463519096375},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.5159895420074463},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5038010478019714},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5036093592643738},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5016646385192871},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.49239885807037354},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4837243854999542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3783763349056244},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.34477150440216064},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12654855847358704},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2124509324","https://openalex.org/W2547875792","https://openalex.org/W2797583228","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2962739339","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W3015265920","https://openalex.org/W3016011332","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3112034174","https://openalex.org/W3197580070","https://openalex.org/W3203140070","https://openalex.org/W3206252155","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4226020322","https://openalex.org/W4297808394","https://openalex.org/W4313156423","https://openalex.org/W4319862700","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6678775411","https://openalex.org/W6729448088","https://openalex.org/W6739901393","https://openalex.org/W6750665317","https://openalex.org/W6755207826","https://openalex.org/W6769238691","https://openalex.org/W6775396121","https://openalex.org/W6780218876","https://openalex.org/W6786669483","https://openalex.org/W6810007534","https://openalex.org/W6846177407"],"related_works":["https://openalex.org/W2742860341","https://openalex.org/W1967145194","https://openalex.org/W3162567751","https://openalex.org/W1982386018","https://openalex.org/W4239601052","https://openalex.org/W4285260836","https://openalex.org/W4319309271","https://openalex.org/W4361193208","https://openalex.org/W4375868863","https://openalex.org/W4323706317"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,73],"representation":[2],"learning":[3,145],"(S3RL)":[4],"is":[5,138],"revolutionizing":[6],"the":[7,11,38,71,77,82,125],"way":[8],"we":[9,24],"leverage":[10],"ever-growing":[12],"availability":[13],"of":[14,33,40,127],"data.":[15],"While":[16],"S3RL":[17,41,86,128,137],"related":[18],"studies":[19],"typically":[20],"use":[21],"large":[22],"models,":[23],"employ":[25],"light-weight":[26,131],"networks":[27],"to":[28,57,81,88,94,110,130,142],"comply":[29],"with":[30,50,103],"tight":[31],"memory":[32],"compute-constrained":[34],"devices.":[35],"We":[36,121],"demonstrate":[37],"effectiveness":[39],"on":[42,67],"a":[43,55,89,139],"keyword-spotting":[44],"(KS)":[45],"problem":[46],"by":[47],"using":[48],"transformers":[49],"330k":[51],"parameters":[52],"and":[53,135],"propose":[54],"mechanism":[56],"enhance":[58],"utterance-wise":[59],"distinction,":[60],"which":[61],"proves":[62],"crucial":[63],"for":[64,133,146],"improving":[65],"performance":[66],"classification":[68],"tasks.":[69],"On":[70,98],"Google":[72],"commands":[74],"v2":[75],"dataset,":[76],"proposed":[78],"method":[79],"applied":[80],"Auto-Regressive":[83],"Predictive":[84],"Coding":[85],"led":[87],"1.2%":[90],"accuracy":[91],"improvement":[92,115],"compared":[93],"training":[95],"from":[96],"scratch.":[97],"an":[99],"in-house":[100],"KS":[101,134],"dataset":[102],"four":[104],"different":[105],"keywords,":[106],"it":[107],"provided":[108],"6%":[109],"23.7%":[111],"relative":[112],"false":[113,118],"accept":[114],"at":[116],"fixed":[117],"reject":[119],"rate.":[120],"argue":[122],"this":[123],"demonstrates":[124],"applicability":[126],"approaches":[129],"models":[132],"confirms":[136],"powerful":[140],"alternative":[141],"traditional":[143],"supervised":[144],"resource-constrained":[147],"applications.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}