{"id":"https://openalex.org/W4415707822","doi":"https://doi.org/10.1109/icme59968.2025.11209914","title":"Zero-Shot Speech Perception Decoding via Advancing Representation Consistency","display_name":"Zero-Shot Speech Perception Decoding via Advancing Representation Consistency","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415707822","doi":"https://doi.org/10.1109/icme59968.2025.11209914"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5083462209","display_name":"Yi Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Xiao","raw_affiliation_strings":["Beijing Normal University,School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":null,"display_name":"XuYi Qiao","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XuYi Qiao","raw_affiliation_strings":["Beijing Normal University,School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110622737","display_name":"Yu-Xuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Xuan Zhang","raw_affiliation_strings":["Beijing Normal University,State Key Laboratory of Cognitive Neuroscience and Learning,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University,State Key Laboratory of Cognitive Neuroscience and Learning,China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101778277","display_name":"Xianchuan Yu","orcid":"https://orcid.org/0000-0003-0742-5135"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianchuan Yu","raw_affiliation_strings":["Beijing Normal University,School of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"Beijing Normal University,School of Artificial Intelligence,China","institution_ids":["https://openalex.org/I25254941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083462209"],"corresponding_institution_ids":["https://openalex.org/I25254941"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31485335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.2985000014305115,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.2985000014305115,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.13910000026226044,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.11540000140666962,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7242000102996826},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6284000277519226},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5547999739646912},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.48170000314712524},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4812000095844269},{"id":"https://openalex.org/keywords/neural-decoding","display_name":"Neural decoding","score":0.45419999957084656},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4453999996185303},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.41040000319480896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512999773025513},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7242000102996826},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5866000056266785},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5547999739646912},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5055999755859375},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.48170000314712524},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47909998893737793},{"id":"https://openalex.org/C40743351","wikidata":"https://www.wikidata.org/wiki/Q7002049","display_name":"Neural decoding","level":3,"score":0.45419999957084656},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.40389999747276306},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.26420000195503235},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2955728019","https://openalex.org/W3161343553","https://openalex.org/W4312933868","https://openalex.org/W4367609927","https://openalex.org/W4386075821","https://openalex.org/W4387378260","https://openalex.org/W4387757582","https://openalex.org/W4389306898","https://openalex.org/W4399563755","https://openalex.org/W4400647281"],"related_works":[],"abstract_inverted_index":{"Non-invasive":[0],"neural":[1,70,154],"activity":[2,27],"decoding":[3,122],"of":[4,10,147],"speech":[5,157],"perception":[6],"(e.g.,":[7],"MEG)":[8],"is":[9],"great":[11],"significance":[12],"for":[13],"both":[14],"artificial":[15],"intelligence":[16],"and":[17,39,61,69,92,116,124],"cognitive":[18],"neuroscience.":[19],"Multimodal":[20],"contrastive":[21],"learning":[22],"(MCL)":[23],"aligns":[24],"trainable":[25],"brain":[26],"representations":[28],"with":[29],"pre-trained":[30],"model":[31,120],"representations,":[32],"reducing":[33],"reliance":[34],"on":[35],"scarce":[36],"MEG":[37],"data":[38],"yielding":[40],"promising":[41],"results.":[42],"However,":[43],"existing":[44],"methods":[45],"still":[46],"face":[47],"limitations":[48],"in":[49,131],"modeling":[50],"cross-modal":[51,76,98,107,135],"consistency,":[52],"primarily":[53],"due":[54],"to":[55,74,96],"inherent":[56],"distributional":[57],"discrepancies,":[58],"semantic":[59],"misalignment,":[60],"noise":[62],"between":[63],"modalities":[64],"such":[65],"as":[66],"audio":[67],"signals":[68],"data,":[71],"which":[72,90],"lead":[73],"biased":[75],"mappings.":[77],"To":[78],"address":[79],"these":[80],"challenges,":[81],"we":[82],"propose":[83],"an":[84],"Aligned":[85],"Audio-MEG":[86],"Decoding":[87],"Network":[88],"(AADN),":[89],"minimizes":[91],"maximizes":[93],"mutual":[94],"information":[95],"separate":[97],"consistency":[99,108],"features":[100],"from":[101],"modality-specific":[102],"features,":[103,118],"thereby":[104],"constructing":[105],"a":[106,132,144],"representation":[109],"space.":[110],"Additionally,":[111],"by":[112],"hierarchically":[113],"integrating":[114],"coarse-grained":[115],"fine-grained":[117],"the":[119,141,153],"improves":[121],"accuracy":[123,146],"generalization":[125],"capability.":[126],"Experimental":[127],"results":[128],"show":[129],"that,":[130],"zero-shot":[133],"audio-MEG":[134],"retrieval":[136],"task":[137],"involving":[138],"1,000":[139],"words,":[140],"framework":[142],"achieves":[143],"top-1":[145],"43.1%,":[148],"providing":[149],"new":[150],"insights":[151],"into":[152],"mechanisms":[155],"underlying":[156],"perception.":[158]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-30T00:00:00"}