{"id":"https://openalex.org/W4408354599","doi":"https://doi.org/10.1109/icassp49660.2025.10887735","title":"Naturalistic Music Decoding from EEG Data via Latent Diffusion Models","display_name":"Naturalistic Music Decoding from EEG Data via Latent Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354599","doi":"https://doi.org/10.1109/icassp49660.2025.10887735"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5069620223","display_name":"Emilian Postolache","orcid":"https://orcid.org/0000-0002-4785-5204"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Emilian Postolache","raw_affiliation_strings":["DAIS Ca' Foscari University of Venice Venice,Italy"],"affiliations":[{"raw_affiliation_string":"DAIS Ca' Foscari University of Venice Venice,Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003706120","display_name":"Natalia Polouliakh","orcid":"https://orcid.org/0000-0001-8266-2697"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Natalia Polouliakh","raw_affiliation_strings":["Sony CSL,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony CSL,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101163591","display_name":"Hiroaki Kitano","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Kitano","raw_affiliation_strings":["Sony CSL,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony CSL,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076516480","display_name":"Akima Connelly","orcid":"https://orcid.org/0000-0001-6480-1278"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akima Connelly","raw_affiliation_strings":["Tokyo Institute of Technology,Dept. of TSE,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Dept. of TSE,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087051832","display_name":"Emanuele Rodol\u00e0","orcid":"https://orcid.org/0000-0003-0091-7241"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Rodol\u00e0","raw_affiliation_strings":["Sapienza University of Rome,Dept. of Computer Science,Rome,Italy"],"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. of Computer Science,Rome,Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085428440","display_name":"Luca Cosmo","orcid":"https://orcid.org/0000-0001-7729-4666"},"institutions":[{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Cosmo","raw_affiliation_strings":["DAIS Ca' Foscari University of Venice Venice,Italy"],"affiliations":[{"raw_affiliation_string":"DAIS Ca' Foscari University of Venice Venice,Italy","institution_ids":["https://openalex.org/I149461666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087426444","display_name":"Taketo Akama","orcid":"https://orcid.org/0009-0007-6971-2777"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taketo Akama","raw_affiliation_strings":["Sony CSL,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony CSL,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069620223"],"corresponding_institution_ids":["https://openalex.org/I149461666"],"apc_list":null,"apc_paid":null,"fwci":6.3826,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95979559,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9922999739646912,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9833999872207642,"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/decoding-methods","display_name":"Decoding methods","score":0.8102370500564575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6879701018333435},{"id":"https://openalex.org/keywords/electroencephalography","display_name":"Electroencephalography","score":0.6798692345619202},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46739229559898376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38355720043182373},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20099860429763794},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11424252390861511},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08107155561447144}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8102370500564575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6879701018333435},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.6798692345619202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46739229559898376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38355720043182373},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20099860429763794},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11424252390861511},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08107155561447144}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.unive.it:10278/5113189","is_oa":false,"landing_page_url":"https://hdl.handle.net/10278/5113189","pdf_url":null,"source":{"id":"https://openalex.org/S4306402336","display_name":"ARCA (Universit\u00e0 Ca' Foscari Venezia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149461666","host_organization_name":"Ca' Foscari University of Venice","host_organization_lineage":["https://openalex.org/I149461666"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2064675550","https://openalex.org/W2526050071","https://openalex.org/W2972478942","https://openalex.org/W4307323391","https://openalex.org/W4312933868","https://openalex.org/W4315701836","https://openalex.org/W4372260310","https://openalex.org/W4372263438","https://openalex.org/W4372266552","https://openalex.org/W4372341629","https://openalex.org/W4375869358","https://openalex.org/W4385834631","https://openalex.org/W4387378260","https://openalex.org/W4390873054","https://openalex.org/W4392902957","https://openalex.org/W4392903391","https://openalex.org/W4392904047","https://openalex.org/W4392904237","https://openalex.org/W4392910528","https://openalex.org/W4393148052","https://openalex.org/W4396877837","https://openalex.org/W4401023775","https://openalex.org/W4405439871","https://openalex.org/W4408345573","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6673899010","https://openalex.org/W6746265271","https://openalex.org/W6765775151","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783713337","https://openalex.org/W6795288823","https://openalex.org/W6796588791","https://openalex.org/W6841982715","https://openalex.org/W6848854281","https://openalex.org/W6849105126","https://openalex.org/W6849517043","https://openalex.org/W6853825612","https://openalex.org/W6854841517","https://openalex.org/W6855255915","https://openalex.org/W6861353174","https://openalex.org/W6875493355"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2922348724","https://openalex.org/W200322357","https://openalex.org/W2390279801","https://openalex.org/W2130428257","https://openalex.org/W4391913857","https://openalex.org/W4308951944","https://openalex.org/W2358668433"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"explore":[4],"the":[5,19,42,90,103,120,132],"potential":[6],"of":[7,14,21,53,74,134],"using":[8,76,135],"latent":[9],"diffusion":[10],"models,":[11,17],"a":[12,50],"family":[13],"powerful":[15],"generative":[16],"for":[18,92,138],"task":[20],"reconstructing":[22],"naturalistic":[23],"music":[24,31,48,72],"from":[25],"electroencephalogram":[26],"(EEG)":[27],"recordings.":[28],"Unlike":[29],"simpler":[30],"with":[32],"limited":[33],"timbres,":[34],"such":[35],"as":[36],"MIDI-generated":[37],"tunes":[38],"or":[39],"monophonic":[40],"pieces,":[41],"focus":[43],"here":[44],"is":[45],"on":[46,86,102],"intricate":[47],"featuring":[49],"diverse":[51],"array":[52],"instruments,":[54],"voices,":[55],"and":[56,61,95,108,126],"effects,":[57],"rich":[58],"in":[59,123],"harmonics":[60],"timbre.":[62],"This":[63],"study":[64],"represents":[65],"an":[66,81],"initial":[67],"foray":[68],"into":[69,131],"achieving":[70],"general":[71],"reconstruction":[73],"high-quality":[75],"non-invasive":[77],"EEG":[78,136],"data,":[79],"employing":[80],"end-to-end":[82],"training":[83],"approach":[84],"directly":[85],"raw":[87],"data":[88,137],"without":[89],"need":[91],"manual":[93],"pre-processing":[94],"channel":[96],"selection.":[97],"We":[98],"train":[99],"our":[100],"models":[101],"public":[104],"NMED-":[105],"T":[106],"dataset":[107],"perform":[109],"quantitative":[110],"evaluation":[111],"proposing":[112],"neural":[113,124],"embedding-based":[114],"metrics.":[115],"Our":[116],"work":[117],"contributes":[118],"to":[119],"ongoing":[121],"research":[122],"decoding":[125],"brain-computer":[127],"interfaces,":[128],"offering":[129],"insights":[130],"feasibility":[133],"complex":[139],"auditory":[140],"information":[141],"reconstruction.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}