{"id":"https://openalex.org/W4415432743","doi":"https://doi.org/10.21437/interspeech.2025-2776","title":"Brain-tuned Speech Models Better Reflect Speech Processing Stages in the Brain","display_name":"Brain-tuned Speech Models Better Reflect Speech Processing Stages in the Brain","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432743","doi":"https://doi.org/10.21437/interspeech.2025-2776"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2776","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/21.11116/0000-0011-90FE-C","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104217084","display_name":"Omer Moussa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omer Moussa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072973927","display_name":"Mariya Toneva","orcid":"https://orcid.org/0000-0002-2407-9871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mariya Toneva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6126,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89449541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2905","last_page":"2909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.92330002784729,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.92330002784729,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44699999690055847},{"id":"https://openalex.org/keywords/neurocomputational-speech-processing","display_name":"Neurocomputational speech processing","score":0.3296999931335449},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.32679998874664307},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.31310001015663147},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.29989999532699585}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.552299976348877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5292999744415283},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44699999690055847},{"id":"https://openalex.org/C202101335","wikidata":"https://www.wikidata.org/wiki/Q7002166","display_name":"Neurocomputational speech processing","level":4,"score":0.3296999931335449},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3160000145435333},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2808000147342682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.26409998536109924}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2776","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.mpg.de:item_3662034","is_oa":true,"landing_page_url":"https://hdl.handle.net/21.11116/0000-0011-90FC-E","pdf_url":"https://hdl.handle.net/21.11116/0000-0011-90FE-C","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/workingPaper"}],"best_oa_location":{"id":"pmh:oai:pure.mpg.de:item_3662034","is_oa":true,"landing_page_url":"https://hdl.handle.net/21.11116/0000-0011-90FC-E","pdf_url":"https://hdl.handle.net/21.11116/0000-0011-90FE-C","source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/workingPaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415432743.pdf","grobid_xml":"https://content.openalex.org/works/W4415432743.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pretrained":[0],"self-supervised":[1],"speech":[2,6,16,44,62,137],"models":[3,38,54,71,76,112],"excel":[4],"in":[5,23,29,77],"tasks":[7],"but":[8,117],"do":[9],"not":[10,113],"reflect":[11,56],"the":[12,57,101],"hierarchy":[13],"of":[14,61,69],"human":[15,40,136],"processing,":[17],"as":[18],"they":[19],"encode":[20],"rich":[21],"semantics":[22,28],"middle":[24],"layers":[25,68,90,99],"and":[26],"poor":[27],"late":[30,67,98],"layers.":[31],"Recent":[32],"work":[33],"showed":[34],"that":[35,66,88,110],"brain-tuning":[36],"(fine-tuning":[37],"using":[39],"brain":[41],"recordings)":[42],"improves":[43],"models'":[45],"semantic":[46,81,128],"understanding.":[47],"Here,":[48],"we":[49],"examine":[50],"how":[51],"well":[52],"brain-tuned":[53,70,111],"further":[55],"brain's":[58],"intermediate":[59],"stages":[60],"processing.":[63,138],"We":[64],"find":[65],"substantially":[72],"improve":[73],"over":[74],"pretrained":[75],"their":[78],"alignment":[79],"with":[80],"language":[82],"regions.":[83],"Further":[84],"layer-wise":[85],"probing":[86],"reveals":[87],"early":[89],"remain":[91],"dedicated":[92],"to":[93,127],"low-level":[94],"acoustic":[95,126],"features,":[96],"while":[97],"become":[100],"best":[102],"at":[103],"complex":[104],"high-level":[105],"tasks.":[106],"These":[107],"findings":[108],"show":[109],"only":[114],"perform":[115],"better":[116,132],"also":[118],"exhibit":[119],"a":[120],"well-defined":[121],"hierarchical":[122],"processing":[123],"going":[124],"from":[125],"representations,":[129],"making":[130],"them":[131],"model":[133],"organisms":[134],"for":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-24T00:00:00"}