{"id":"https://openalex.org/W4319862456","doi":"https://doi.org/10.1109/slt54892.2023.10023410","title":"Match to Win: Analysing Sequences Lengths for Efficient Self-Supervised Learning in Speech and Audio","display_name":"Match to Win: Analysing Sequences Lengths for Efficient Self-Supervised Learning in Speech and Audio","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862456","doi":"https://doi.org/10.1109/slt54892.2023.10023410"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023410","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5082863098","display_name":"Yan Gaol","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yan Gaol","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031116318","display_name":"Javier Fern\u00e1ndez-Marqu\u00e9s","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Javier Fernandez-Marques","raw_affiliation_strings":["Samsung AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089505434","display_name":"Titouan Parcollet","orcid":"https://orcid.org/0000-0003-0672-1346"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Titouan Parcollet","raw_affiliation_strings":["Avignon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Avignon University","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110718216","display_name":"Pedro Porto Buarque de Gusm\u00e3o","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pedro P. B. de Gusmao","raw_affiliation_strings":["University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045638679","display_name":"Nicholas D. Lane","orcid":"https://orcid.org/0000-0002-2728-8273"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Nicholas D. Lane","raw_affiliation_strings":["University of Cambridge","Samsung AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Samsung AI","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"122"},"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":0.9994000196456909,"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":0.998199999332428,"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":0.8416324257850647},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5584838390350342},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5437653064727783},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5129460692405701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49960947036743164},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.49952030181884766},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.4379117786884308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4274352490901947},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4161298871040344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3681927025318146},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15365147590637207},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1227630078792572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8416324257850647},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5584838390350342},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5437653064727783},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5129460692405701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49960947036743164},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.49952030181884766},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4379117786884308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4274352490901947},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4161298871040344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3681927025318146},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15365147590637207},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1227630078792572},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023410","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2146334809","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2797583228","https://openalex.org/W2890964092","https://openalex.org/W2892009249","https://openalex.org/W2979826702","https://openalex.org/W2981087920","https://openalex.org/W3015213852","https://openalex.org/W3036601975","https://openalex.org/W3148040514","https://openalex.org/W3167533889","https://openalex.org/W3190342989","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221145109","https://openalex.org/W4283821485","https://openalex.org/W4287121455","https://openalex.org/W4296070200","https://openalex.org/W6631190155","https://openalex.org/W6745245109","https://openalex.org/W6750665317","https://openalex.org/W6780218876","https://openalex.org/W6793680709","https://openalex.org/W6796551075","https://openalex.org/W6810007534","https://openalex.org/W6839435366"],"related_works":["https://openalex.org/W4205505298","https://openalex.org/W3191281725","https://openalex.org/W3042492850","https://openalex.org/W3106610906","https://openalex.org/W4292394195","https://openalex.org/W3106904549","https://openalex.org/W4311454612","https://openalex.org/W3185724185","https://openalex.org/W4316042121","https://openalex.org/W2989221764"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"has":[3],"proven":[4],"vital":[5],"in":[6],"speech":[7],"and":[8,96,144],"audio-related":[9],"applications.":[10,146],"The":[11],"paradigm":[12],"trains":[13],"a":[14,117],"general":[15],"model":[16,33,63],"on":[17,107],"unlabeled":[18],"data":[19,135],"that":[20,45,105],"can":[21,46,110],"later":[22],"be":[23,48],"used":[24],"to":[25,36,58,72,99,137],"solve":[26],"specific":[27],"downstream":[28,101],"tasks.":[29,102,122],"This":[30,123],"type":[31],"of":[32,67,88,131],"is":[34],"costly":[35],"train":[37],"as":[38],"it":[39],"requires":[40],"manipulating":[41],"long":[42],"input":[43,69],"sequences":[44,109],"only":[47],"handled":[49],"by":[50],"powerful":[51],"centralised":[52],"servers.":[53],"Surprisingly,":[54],"despite":[55],"many":[56],"attempts":[57],"increase":[59],"training":[60,106,133],"efficiency":[61],"through":[62],"compression,":[64],"the":[65,84,129],"effects":[66],"truncating":[68],"sequence":[70,94],"lengths":[71,95],"reduce":[73,112],"computation":[74],"have":[75],"not":[76],"been":[77],"studied.":[78],"In":[79],"this":[80,98],"paper,":[81],"we":[82],"provide":[83],"first":[85],"empirical":[86],"study":[87],"SSL":[89,132],"pre-training":[90],"for":[91,120,141],"different":[92],"specified":[93],"link":[97],"various":[100],"We":[103],"find":[104],"short":[108],"dramatically":[111],"resource":[113],"costs":[114],"while":[115],"retaining":[116],"satisfactory":[118],"performance":[119],"all":[121],"simple":[124],"one-line":[125],"change":[126],"would":[127],"promote":[128],"migration":[130],"from":[134],"centres":[136],"user-end":[138],"edge":[139],"devices":[140],"more":[142],"realistic":[143],"personalised":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}