{"id":"https://openalex.org/W4392903871","doi":"https://doi.org/10.1109/icassp48485.2024.10446334","title":"Do Self-Supervised Speech and Language Models Extract Similar Representations as Human Brain?","display_name":"Do Self-Supervised Speech and Language Models Extract Similar Representations as Human Brain?","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903871","doi":"https://doi.org/10.1109/icassp48485.2024.10446334"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446334","doi":"https://doi.org/10.1109/icassp48485.2024.10446334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446334","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.04645","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Peili Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peili Chen","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","School of Biomedical Engineering, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Biomedical Engineering, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100549976","display_name":"Linyang He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linyang He","raw_affiliation_strings":["University of Michigan,Department of Electrical Engineering and Computer Science,Ann Arbor,MI,USA","Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical Engineering and Computer Science,Ann Arbor,MI,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101865288","display_name":"Li Fu","orcid":"https://orcid.org/0000-0002-7533-692X","observed_orcids":["https://orcid.org/0000-0002-7533-692X"]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Fu","raw_affiliation_strings":["JD AI Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371061","display_name":"Lu Fan","orcid":"https://orcid.org/0009-0002-9253-0019","observed_orcids":["https://orcid.org/0009-0002-9253-0019"]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Fan","raw_affiliation_strings":["JD AI Research, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091099837","display_name":"Edward F. Chang","orcid":"https://orcid.org/0000-0003-2480-4700","observed_orcids":["https://orcid.org/0000-0003-2480-4700"]},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward F. Chang","raw_affiliation_strings":["University of California,Department of Neurological Surgery,San Francisco,CA,USA","Department of Neurological Surgery, University of California, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Neurological Surgery,San Francisco,CA,USA","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"Department of Neurological Surgery, University of California, San Francisco, CA, USA","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101397818","display_name":"Yuanning Li","orcid":"https://orcid.org/0000-0003-3277-0600","observed_orcids":["https://orcid.org/0000-0003-3277-0600"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanning Li","raw_affiliation_strings":["ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","School of Biomedical Engineering, ShanghaiTech University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,School of Biomedical Engineering,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]},{"raw_affiliation_string":"School of Biomedical Engineering, ShanghaiTech University, Shanghai, China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0155,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.93767399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2225","last_page":"2229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.5073000192642212,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.5073000192642212,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3855000138282776,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.025499999523162842,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/self-supervised-speech-models","display_name":"self-supervised speech models","score":0.8429999947547913},{"id":"https://openalex.org/keywords/auditory-cortex","display_name":"auditory cortex","score":0.671999990940094},{"id":"https://openalex.org/keywords/speech-perception","display_name":"speech perception","score":0.8009999990463257},{"id":"https://openalex.org/keywords/wav2vec-2-0","display_name":"wav2vec 2.0","score":0.8109999895095825},{"id":"https://openalex.org/keywords/gpt-2","display_name":"GPT-2","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7144687175750732},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.6042258143424988},{"id":"https://openalex.org/C202101335","wikidata":"https://www.wikidata.org/wiki/Q7002166","display_name":"Neurocomputational speech processing","level":4,"score":0.5266145467758179},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.505957305431366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5006506443023682},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4936898648738861},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4824298322200775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48119622468948364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46985259652137756},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.44230854511260986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43588370084762573},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23810839653015137},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0871199369430542},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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":3,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446334","doi":"https://doi.org/10.1109/icassp48485.2024.10446334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446334","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.04645","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.04645","pdf_url":"https://arxiv.org/pdf/2310.04645","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.04645","doi":"https://doi.org/10.48550/arxiv.2310.04645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.04645","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.04645","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.04645","pdf_url":"https://arxiv.org/pdf/2310.04645","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392903871.pdf","grobid_xml":"https://content.openalex.org/works/W4392903871.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W1965248225","https://openalex.org/W2025341678","https://openalex.org/W2082183045","https://openalex.org/W2171525519","https://openalex.org/W2250539671","https://openalex.org/W2787560479","https://openalex.org/W2896457183","https://openalex.org/W2951670472","https://openalex.org/W3036601975","https://openalex.org/W3086360455","https://openalex.org/W3169320628","https://openalex.org/W3179803166","https://openalex.org/W3210923133","https://openalex.org/W4200630739","https://openalex.org/W4220949944","https://openalex.org/W4310157637","https://openalex.org/W4388034436","https://openalex.org/W4389519451","https://openalex.org/W6780218876","https://openalex.org/W7133198220"],"related_works":["https://openalex.org/W4405905832","https://openalex.org/W4402454427","https://openalex.org/W4281765823","https://openalex.org/W4404783855","https://openalex.org/W7223437323","https://openalex.org/W4400645798","https://openalex.org/W4402112234","https://openalex.org/W4385822399","https://openalex.org/W4392904752","https://openalex.org/W4407759713"],"abstract_inverted_index":{"Speech":[0],"and":[1,17,54,59,91,106,122,139,145],"language":[2,18,60,146],"models":[3,67,121,138],"trained":[4],"through":[5],"self-supervised":[6],"learning":[7],"(SSL)":[8],"demonstrate":[9],"strong":[10],"alignment":[11,124],"with":[12,32,76,125],"brain":[13,45,82,101],"activity":[14],"during":[15],"speech":[16,58,70,86,116,130,144],"perception.":[19],"However,":[20],"given":[21],"their":[22,81,123],"distinct":[23],"training":[24],"modalities,":[25],"it":[26],"remains":[27],"unclear":[28],"whether":[29],"they":[30],"correlate":[31],"the":[33,44,73,95,113,126,140],"same":[34],"neural":[35,127,141],"aspects.":[36],"We":[37],"directly":[38],"address":[39],"this":[40],"question":[41],"by":[42],"evaluating":[43],"prediction":[46],"performance":[47],"of":[48,97,115,143],"two":[49],"representative":[50],"SSL":[51,120,137],"models,":[52],"Wav2Vec2.0":[53,90],"GPT-2,":[55],"designed":[56],"for":[57,94],"tasks.":[61],"Our":[62],"findings":[63],"reveal":[64],"that":[65],"both":[66,136],"accurately":[68],"predict":[69],"responses":[71],"in":[72,100,119],"auditory":[74],"cortex,":[75],"a":[77],"significant":[78],"correlation":[79],"between":[80,89],"predictions.":[83],"Notably,":[84],"shared":[85],"contextual":[87,117],"information":[88],"GPT-2":[92],"accounts":[93],"majority":[96],"explained":[98],"variance":[99],"activity,":[102],"surpassing":[103],"static":[104],"semantic":[105],"lower-level":[107],"acoustic-phonetic":[108],"information.":[109],"These":[110],"results":[111],"underscore":[112],"convergence":[114],"representations":[118],"network":[128],"underlying":[129],"perception,":[131],"offering":[132],"valuable":[133],"insights":[134],"into":[135],"basis":[142],"processing.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-03-19T00:00:00"}
