{"id":"https://openalex.org/W3162133897","doi":"https://doi.org/10.1109/icassp39728.2021.9414321","title":"Similarity Analysis of Self-Supervised Speech Representations","display_name":"Similarity Analysis of Self-Supervised Speech Representations","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162133897","doi":"https://doi.org/10.1109/icassp39728.2021.9414321","mag":"3162133897"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414321","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":"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/A5008107321","display_name":"Yu-An Chung","orcid":"https://orcid.org/0000-0001-9451-7956"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu-An Chung","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051184573","display_name":"Yonatan Belinkov","orcid":null},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yonatan Belinkov","raw_affiliation_strings":["Technion Henry and Marilyn Taub Faculty of Computer Science, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion Henry and Marilyn Taub Faculty of Computer Science, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3040","last_page":"3044"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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":0.9977999925613403,"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":0.7368366718292236},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.676685631275177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5805715322494507},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.545747697353363},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5419467687606812},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5121871829032898},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49232685565948486},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4464718699455261},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4255399703979492},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.42341750860214233},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25540226697921753},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13665461540222168}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368366718292236},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.676685631275177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805715322494507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.545747697353363},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5419467687606812},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5121871829032898},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49232685565948486},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4464718699455261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4255399703979492},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.42341750860214233},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25540226697921753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13665461540222168},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414321","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1523385540","https://openalex.org/W2152790380","https://openalex.org/W2160654481","https://openalex.org/W2748318213","https://openalex.org/W2752168051","https://openalex.org/W2767204723","https://openalex.org/W2842511635","https://openalex.org/W2936774411","https://openalex.org/W2942810103","https://openalex.org/W2962739339","https://openalex.org/W2962813140","https://openalex.org/W2963341956","https://openalex.org/W2963503967","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W2998649947","https://openalex.org/W3003875258","https://openalex.org/W3005680577","https://openalex.org/W3015265920","https://openalex.org/W3015356564","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3026957705","https://openalex.org/W3034487470","https://openalex.org/W3035202887","https://openalex.org/W3036601975","https://openalex.org/W3040997499","https://openalex.org/W3041561163","https://openalex.org/W3044483536","https://openalex.org/W3049256661","https://openalex.org/W3096485810","https://openalex.org/W3096656254","https://openalex.org/W3097053302","https://openalex.org/W3097286738","https://openalex.org/W3097787369","https://openalex.org/W3099782249","https://openalex.org/W3160345865","https://openalex.org/W4297730150","https://openalex.org/W4297808394","https://openalex.org/W6631216910","https://openalex.org/W6682948231","https://openalex.org/W6743489131","https://openalex.org/W6745682157","https://openalex.org/W6755641643","https://openalex.org/W6761472960","https://openalex.org/W6769238691","https://openalex.org/W6771812881","https://openalex.org/W6772641181","https://openalex.org/W6774314701","https://openalex.org/W6777372923","https://openalex.org/W6777859476","https://openalex.org/W6780218876","https://openalex.org/W6780361010"],"related_works":["https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2381021552","https://openalex.org/W2354749003","https://openalex.org/W2377121353","https://openalex.org/W2350529538","https://openalex.org/W2366015234","https://openalex.org/W2899909497"],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,32,102],"representation":[2,136],"learning":[3,17],"has":[4,40,131],"recently":[5],"been":[6,14,36,41],"a":[7,28,59,132,156],"prosperous":[8],"research":[9,43],"topic.":[10],"Many":[11],"algorithms":[12],"have":[13,34],"proposed":[15],"for":[16,165],"useful":[18],"representations":[19,78],"from":[20],"large-scale":[21],"unlabeled":[22],"data,":[23],"and":[24,97,146,162],"their":[25,106],"applications":[26],"to":[27,57,88,111],"wide":[29],"range":[30],"of":[31,49,62,64,100],"tasks":[33,87],"also":[35,84,125,151],"investigated.":[37],"However,":[38],"there":[39,154],"little":[42],"focusing":[44],"on":[45,135],"understanding":[46],"the":[47,65,73,90,93,98,120,128],"properties":[48],"existing":[50,80],"approaches.":[51],"In":[52,109],"this":[53],"work,":[54],"we":[55,71],"aim":[56],"provide":[58],"comparative":[60],"study":[61,89,124],"some":[63,166],"most":[66],"representative":[67],"self-supervised":[68,77,115,167],"algorithms.":[69,168],"Specifically,":[70],"quantify":[72],"similarities":[74],"between":[75,92,159],"different":[76],"using":[79],"similarity":[81,137],"measures.":[82],"We":[83],"design":[85],"probing":[86],"correlation":[91,158],"models\u2019":[94],"pre-training":[95,160],"loss":[96,161],"amount":[99],"specific":[101],"information":[103],"contained":[104],"in":[105],"learned":[107],"representations.":[108],"addition":[110],"showing":[112],"how":[113],"various":[114],"models":[116],"behave":[117],"differently":[118],"given":[119],"same":[121],"input,":[122],"our":[123],"finds":[126],"that":[127,153],"training":[129],"objective":[130],"higher":[133],"impact":[134],"than":[138],"architectural":[139],"choices":[140],"such":[141],"as":[142],"building":[143],"blocks":[144],"(RNN/Transformer/CNN)":[145],"directionality":[147],"(uni/bidirectional).":[148],"Our":[149],"results":[150],"suggest":[152],"exists":[155],"strong":[157],"downstream":[163],"performance":[164]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}