{"id":"https://openalex.org/W4408347247","doi":"https://doi.org/10.1109/icassp49660.2025.10889637","title":"A Novel Multimodal Method for Decoding Speech Perception from Brain Activities","display_name":"A Novel Multimodal Method for Decoding Speech Perception from Brain Activities","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347247","doi":"https://doi.org/10.1109/icassp49660.2025.10889637"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889637","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":null,"display_name":"Aoke Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Aoke Zhang","raw_affiliation_strings":["Peking University,Speech and Hearing Research Center, School of Intelligence Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Speech and Hearing Research Center, School of Intelligence Science and Technology,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063283077","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0002-3231-1167"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":["Peking University,Speech and Hearing Research Center, School of Intelligence Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Speech and Hearing Research Center, School of Intelligence Science and Technology,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110962571","display_name":"WU Xi-hong","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Peking University,Speech and Hearing Research Center, School of Intelligence Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Speech and Hearing Research Center, School of Intelligence Science and Technology,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044632457","display_name":"Jing Chen","orcid":"https://orcid.org/0000-0002-1918-7050"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chen","raw_affiliation_strings":["Peking University,Speech and Hearing Research Center, School of Intelligence Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Speech and Hearing Research Center, School of Intelligence Science and Technology,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.3069,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85951589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9437000155448914,"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":0.9437000155448914,"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":0.7934492826461792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6792362332344055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6391302943229675},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5410804152488708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32261061668395996},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21180394291877747},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.14362499117851257},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1035510003566742}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7934492826461792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6792362332344055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6391302943229675},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5410804152488708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32261061668395996},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21180394291877747},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.14362499117851257},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1035510003566742}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889637","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2051424583","https://openalex.org/W2084333685","https://openalex.org/W2120698894","https://openalex.org/W2194775991","https://openalex.org/W2344975321","https://openalex.org/W2481854178","https://openalex.org/W2782213998","https://openalex.org/W2890072669","https://openalex.org/W2940585064","https://openalex.org/W4220904310","https://openalex.org/W4298143835","https://openalex.org/W4367609927","https://openalex.org/W4386091044","https://openalex.org/W4386100600","https://openalex.org/W4387378260","https://openalex.org/W4401560881","https://openalex.org/W6731370813","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6780218876","https://openalex.org/W6791353385","https://openalex.org/W6846678071"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Decoding":[0],"speech":[1,29,193],"from":[2,78,91,153],"neural":[3],"recordings":[4],"has":[5,24],"critical":[6],"importance":[7],"in":[8,28,102],"application":[9],"and":[10,37,61,71,83,147,165],"scientific":[11],"research.":[12],"However,":[13],"this":[14,46,184],"task":[15,32],"is":[16],"still":[17],"challenging":[18],"with":[19,85,105,114],"non-invasive":[20],"recordings.":[21],"Previous":[22],"research":[23],"shown":[25],"significant":[26],"improvement":[27,119],"perception":[30],"decoding":[31],"by":[33,54,139],"leveraging":[34],"wav2vec":[35,86],"vectors":[36,87],"gives":[38],"the":[39,92,123,126,133,141,154,179,187],"potential":[40,188],"for":[41,69,192],"applications.":[42],"To":[43],"further":[44],"explore":[45],"problem,":[47],"we":[48],"proposed":[49,127],"a":[50,106],"novel":[51],"multimodal":[52,95,190],"method":[53,96],"using":[55],"functional":[56],"magnetic":[57],"resonance":[58],"imaging":[59],"(fMRI)":[60],"magnetoencephalography":[62],"(MEG).":[63],"In":[64],"our":[65],"method,":[66],"separate":[67],"encoders":[68],"fMRI":[70,166],"MEG":[72,159],"are":[73,81],"considered,":[74],"then":[75],"features":[76,151],"extracted":[77,90,152],"both":[79,174],"modalities":[80],"integrated":[82],"aligned":[84],"that":[88,158],"were":[89],"speech.":[93,155],"The":[94,181],"reaches":[97],"averaged":[98],"performance":[99,134],"of":[100,110,125,132,150,183,189],"72.6%":[101],"top-10":[103],"accuracy":[104],"negative":[107],"sample":[108],"size":[109],"128.":[111],"Performance":[112],"evaluated":[113],"various":[115],"metrics":[116],"achieves":[117],"steady":[118],"across":[120],"subjects,":[121],"demonstrating":[122],"effectiveness":[124],"data":[128],"fusion":[129],"method.":[130],"Interpretation":[131],"increment":[135],"was":[136],"also":[137],"investigated":[138],"testing":[140],"correlation":[142],"between":[143],"encoder":[144,160,167],"hidden":[145],"outputs":[146],"different":[148],"level":[149],"Results":[156],"demonstrate":[157],"learns":[161,168],"more":[162,169],"low-level":[163],"information":[164],"high-level":[170],"information,":[171],"which":[172],"indicates":[173],"complementary":[175],"characteristics":[176],"lead":[177],"to":[178],"improvement.":[180],"result":[182],"work":[185],"shows":[186],"methods":[191],"decoding.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-05-22T09:01:20.584952","created_date":"2025-10-10T00:00:00"}