{"id":"https://openalex.org/W4415536862","doi":"https://doi.org/10.1145/3746027.3755501","title":"DMF2Mel: A Dynamic Multiscale Fusion Network for EEG-Driven Mel Spectrogram Reconstruction","display_name":"DMF2Mel: A Dynamic Multiscale Fusion Network for EEG-Driven Mel Spectrogram Reconstruction","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536862","doi":"https://doi.org/10.1145/3746027.3755501"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["School of Computer Science and Technology,State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6318-8803","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology,State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sheng Zhang","orcid":"https://orcid.org/0009-0008-5291-5807"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-5291-5807","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingjing Zhang","orcid":"https://orcid.org/0009-0006-1173-2970"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-1173-2970","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074457534","display_name":"Enrui Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enrui Liu","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0009-2248-9920","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116159413","display_name":"Xinhui Li","orcid":"https://orcid.org/0009-0006-5522-0037"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhui Li","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0006-5522-0037","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073574475","display_name":"Gangming Zhao","orcid":"https://orcid.org/0000-0001-8441-5462"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gangming Zhao","raw_affiliation_strings":["School of Electronics and Information Engineering, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-8441-5462","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Engineering, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026466982","display_name":"Zhao Lv","orcid":"https://orcid.org/0000-0003-4530-4422"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Lv","raw_affiliation_strings":["School of Computer Science and Technology,State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4530-4422","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology,State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I126520041","https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6977","last_page":"6985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9897000193595886,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9897000193595886,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.9811999797821045,"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/spectrogram","display_name":"Spectrogram","score":0.7839000225067139},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5773000121116638},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5648000240325928},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.491100013256073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47859999537467957},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.461899995803833},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40720000863075256},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.3912999927997589},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.38440001010894775},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3824000060558319}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7839000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245000004768372},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5773000121116638},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5648000240325928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5103999972343445},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49309998750686646},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.461899995803833},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3343999981880188},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2143663807","https://openalex.org/W2481854178","https://openalex.org/W2884585870","https://openalex.org/W3016106826","https://openalex.org/W3180220247","https://openalex.org/W3196221522","https://openalex.org/W4200630739","https://openalex.org/W4308523455","https://openalex.org/W4316468787","https://openalex.org/W4362459190","https://openalex.org/W4375868978","https://openalex.org/W4382239589","https://openalex.org/W4392172875","https://openalex.org/W4394577281","https://openalex.org/W4401055959","https://openalex.org/W4401609042","https://openalex.org/W4403780811","https://openalex.org/W4406892576","https://openalex.org/W4407958752"],"related_works":[],"abstract_inverted_index":{"Decoding":[0],"speech":[1],"from":[2,110],"brain":[3],"signals":[4],"is":[5,220],"a":[6,190],"challenging":[7],"research":[8],"problem.":[9],"Although":[10],"existing":[11],"technologies":[12],"have":[13],"made":[14],"progress":[15],"in":[16,34,57,196],"reconstructing":[17],"the":[18,25,35,48,67,79,86,92,97,104,126,134,151,183,207,218],"mel":[19,197],"spectrograms":[20],"of":[21,38,50,75,128,140,194],"auditory":[22],"stimuli":[23],"at":[24],"word":[26],"or":[27],"letter":[28],"level,":[29],"there":[30],"remain":[31],"core":[32,77],"challenges":[33],"precise":[36],"reconstruction":[37,199],"minute-level":[39],"continuous":[40],"imagined":[41],"speech:":[42],"traditional":[43],"models":[44],"struggle":[45],"to":[46,157],"balance":[47],"efficiency":[49],"temporal":[51,170],"dependency":[52],"modeling":[53,161,179],"and":[54,96,117,124,143,175,209],"information":[55],"retention":[56],"long-sequence":[58],"decoding.":[59],"To":[60],"address":[61],"this":[62,64],"issue,":[63],"paper":[65],"proposes":[66],"Dynamic":[68,80],"Multiscale":[69],"Fusion":[70],"Network":[71,90,155],"(DMF2Mel),":[72],"which":[73],"consists":[74],"four":[76],"components:":[78],"Contrastive":[81],"Feature":[82],"Aggregation":[83],"Module":[84],"(DC-FAM),":[85],"Hierarchical":[87],"Attention-Guided":[88],"Multi-Scale":[89],"(HAMS-Net),":[91],"SplineMap":[93,147],"attention":[94,119,148],"mechanism,":[95],"bidirectional":[98],"state":[99],"space":[100],"module":[101],"(convMamba).":[102],"Specifically,":[103],"DC-FAM":[105],"separates":[106],"speech-related":[107],"''foreground":[108],"features''":[109,113],"noisy":[111],"''background":[112],"through":[114],"local":[115,164],"convolution":[116],"global":[118,159],"mechanisms,":[120],"effectively":[121],"suppressing":[122],"interference":[123],"enhancing":[125],"representation":[127],"transient":[129],"signals.":[130],"HAMS-Net,":[131],"based":[132],"on":[133,182],"U-Net":[135],"framework,":[136],"achieves":[137,189],"cross-scale":[138],"fusion":[139],"high-level":[141],"semantics":[142],"low-level":[144],"details.":[145],"The":[146,166],"mechanism":[149],"integrates":[150],"Adaptive":[152],"Gated":[153],"Kolmogorov-Arnold":[154],"(AGKAN)":[156],"combine":[158],"context":[160],"with":[162,172],"spline-based":[163],"fitting.":[165],"convMamba":[167],"captures":[168],"long-range":[169],"dependencies":[171],"linear":[173],"complexity":[174],"enhances":[176],"nonlinear":[177],"dynamic":[178],"capabilities.":[180],"Results":[181],"SparrKULee":[184],"dataset":[185],"show":[186],"that":[187],"DMF2Mel":[188],"Pearson":[191],"correlation":[192],"coefficient":[193],"0.074":[195],"spectrogram":[198],"for":[200,211],"known":[201],"subjects":[202,213],"(a":[203,214],"48%":[204],"improvement":[205,216],"over":[206,217],"baseline)":[208],"0.048":[210],"unknown":[212],"35%":[215],"baseline).Code":[219],"available":[221],"at:":[222],"https://github.com/fchest/DMF2Mel.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-25T00:00:00"}