{"id":"https://openalex.org/W4415433341","doi":"https://doi.org/10.21437/interspeech.2025-1400","title":"Recreating Neural Activity During Speech Production with Language and Speech Model Embeddings","display_name":"Recreating Neural Activity During Speech Production with Language and Speech Model Embeddings","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433341","doi":"https://doi.org/10.21437/interspeech.2025-1400"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1400","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1400","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050310893","display_name":"Owais Mujtaba Khanday","orcid":"https://orcid.org/0000-0002-9855-1809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Owais Mujtaba Khanday","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pablo Rodr\u00edguez San Esteban","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pablo Rodr\u00edguez San Esteban","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120051070","display_name":"Zubair Ahmad Lone","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zubair Ahmad Lone","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055252410","display_name":"Marc Ouellet","orcid":"https://orcid.org/0000-0001-5117-1094"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Ouellet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100720211","display_name":"Jos\u00e9 A. Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-5531-8994"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose A. Gonzalez-Lopez","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":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5553","last_page":"5557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7109000086784363,"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/T12031","display_name":"Speech and dialogue systems","score":0.7109000086784363,"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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.6987000107765198,"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/neural-activity","display_name":"Neural activity","score":0.6402000188827515},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5896999835968018},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5633999705314636},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5266000032424927},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.46399998664855957},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4447999894618988},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.42289999127388},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41749998927116394}],"concepts":[{"id":"https://openalex.org/C2984127161","wikidata":"https://www.wikidata.org/wiki/Q969316","display_name":"Neural activity","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6269999742507935},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5896000266075134},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447000026702881},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C120843803","wikidata":"https://www.wikidata.org/wiki/Q4955807","display_name":"Brain activity and meditation","level":3,"score":0.34929999709129333},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.31610000133514404},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2906999886035919},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2776264592","wikidata":"https://www.wikidata.org/wiki/Q463837","display_name":"Language production","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1400","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1400","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:digibug.ugr.es:10481/105970","is_oa":false,"landing_page_url":"https://hdl.handle.net/10481/105970","pdf_url":null,"source":{"id":"https://openalex.org/S4306400567","display_name":"Institutional Repository of the University of Granada (University of Granada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173304897","host_organization_name":"Universidad de Granada","host_organization_lineage":["https://openalex.org/I173304897"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference output"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"how":[1],"neural":[2,34,83],"activity":[3,35,90,103],"encodes":[4],"speech":[5,28,44,62,110],"and":[6,15,27,56,94,109],"language":[7,26,108],"production":[8],"is":[9],"a":[10],"fundamental":[11],"challenge":[12],"in":[13],"neuroscience":[14],"artificial":[16],"intelligence.":[17],"This":[18],"study":[19],"investigates":[20],"whether":[21],"embeddings":[22,49,74],"from":[23,50],"large-scale,":[24],"self-supervised":[25],"models":[29,53],"can":[30],"effectively":[31,105],"reconstruct":[32],"high-gamma":[33,65,88],"characteristics,":[36],"key":[37],"indicators":[38],"of":[39,79,117],"cortical":[40],"processing,":[41],"recorded":[42],"during":[43],"production.":[45],"We":[46,67],"use":[47],"pre-trained":[48],"deep":[51],"learning":[52],"on":[54],"linguistic":[55],"acoustic":[57],"data":[58],"to":[59,71],"map":[60],"high-level":[61],"features":[63],"onto":[64],"signals.":[66],"analyze":[68],"the":[69,76],"extent":[70],"which":[72],"these":[73],"preserve":[75],"spatio-temporal":[77],"dynamics":[78],"brain":[80],"activity.":[81],"Reconstructed":[82],"signals":[84],"are":[85],"evaluated":[86],"against":[87],"ground-truth":[89],"using":[91,107],"correlation":[92,115],"metrics":[93],"signal":[95],"reconstruction":[96],"quality":[97],"assessments.":[98],"The":[99],"results":[100],"indicate":[101],"High-gamma":[102],"was":[104],"reconstructed":[106],"model":[111],"embeddings,":[112],"yielding":[113],"Pearson":[114],"coefficients":[116],"0.79\u20130.99":[118],"across":[119],"all":[120],"participants.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-23T00:00:00"}