{"id":"https://openalex.org/W4410331260","doi":"https://doi.org/10.3389/fnbot.2025.1568811","title":"TS-Resformer: a model based on multimodal fusion for the classification of music signals","display_name":"TS-Resformer: a model based on multimodal fusion for the classification of music signals","publication_year":2025,"publication_date":"2025-05-13","ids":{"openalex":"https://openalex.org/W4410331260","doi":"https://doi.org/10.3389/fnbot.2025.1568811","pmid":"https://pubmed.ncbi.nlm.nih.gov/40433555"},"language":"en","primary_location":{"id":"doi:10.3389/fnbot.2025.1568811","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2025.1568811","pdf_url":"https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2025.1568811/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2025.1568811/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100758234","display_name":"Yilin Zhang","orcid":"https://orcid.org/0000-0002-4448-0005"},"institutions":[{"id":"https://openalex.org/I156292868","display_name":"Dalian University of Foreign Languages","ror":"https://ror.org/008a8z393","country_code":"CN","type":"education","lineage":["https://openalex.org/I156292868"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yilin Zhang","raw_affiliation_strings":["Dalian University of Foreign Languages, International Art College, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Foreign Languages, International Art College, Dalian, China","institution_ids":["https://openalex.org/I156292868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100758234"],"corresponding_institution_ids":["https://openalex.org/I156292868"],"apc_list":{"value":2950,"currency":"USD","value_usd":2950},"apc_paid":{"value":2950,"currency":"USD","value_usd":2950},"fwci":0.9024,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71043389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"19","issue":null,"first_page":"1568811","last_page":"1568811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9883999824523926,"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/T13996","display_name":"Diverse Musicological Studies","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106334209442139},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.528963029384613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5211870074272156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5185688138008118},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5171696543693542},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5105582475662231},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4982304573059082},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4538896381855011},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.44756168127059937},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.42546790838241577},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11312997341156006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10547080636024475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106334209442139},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.528963029384613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5211870074272156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5185688138008118},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5171696543693542},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5105582475662231},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4982304573059082},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4538896381855011},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.44756168127059937},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.42546790838241577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11312997341156006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10547080636024475},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fnbot.2025.1568811","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2025.1568811","pdf_url":"https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2025.1568811/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},{"id":"pmid:40433555","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40433555","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in neurorobotics","raw_type":null},{"id":"pmh:oai:doaj.org/article:bd1658bc41084963bcfaa2586e48de43","is_oa":true,"landing_page_url":"https://doaj.org/article/bd1658bc41084963bcfaa2586e48de43","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Neurorobotics, Vol 19 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12106318","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12106318","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Neurorobot","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3389/fnbot.2025.1568811","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2025.1568811","pdf_url":"https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2025.1568811/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410331260.pdf","grobid_xml":"https://content.openalex.org/works/W4410331260.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W2117925075","https://openalex.org/W2133824856","https://openalex.org/W2178339699","https://openalex.org/W2514413323","https://openalex.org/W2576489192","https://openalex.org/W2751759753","https://openalex.org/W2799148064","https://openalex.org/W2911484868","https://openalex.org/W2963451564","https://openalex.org/W3000748319","https://openalex.org/W3049459827","https://openalex.org/W3159538208","https://openalex.org/W4206376062","https://openalex.org/W4284887954","https://openalex.org/W4292536266","https://openalex.org/W4292622404","https://openalex.org/W4313334373","https://openalex.org/W4360612734","https://openalex.org/W4381378952","https://openalex.org/W4383342522","https://openalex.org/W4385429841","https://openalex.org/W4390007540","https://openalex.org/W4400743863","https://openalex.org/W4401507722","https://openalex.org/W4403688364","https://openalex.org/W4405993063","https://openalex.org/W4406229963","https://openalex.org/W6600593648","https://openalex.org/W6796752884","https://openalex.org/W6841843731"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2032776242"],"abstract_inverted_index":{"The":[0,207,255],"number":[1,45],"of":[2,4,23,30,35,46,53,66,69,76,80,98,112,175,177,210,250,258,281,309,322,341],"music":[3,24,36,54,70,77,93,99,109,188,271,316],"different":[5,92,113,125,296,307],"genres":[6],"is":[7,15,146,161,216,344,351],"increasing":[8],"year":[9],"by":[10,163],"year,":[11],"and":[12,17,84,128,134,151,155,168,183,228,232,264,299,324],"manual":[13],"classification":[14,185,279,355],"costly":[16],"requires":[18],"professionals":[19],"in":[20,50,187,354],"the":[21,33,51,57,64,89,96,143,157,165,173,199,203,213,223,234,237,247,251,259,267,278,282,286,291,301,314,319,327,330,339,347,359],"field":[22,52],"to":[25,245,269,275,311,329],"manually":[26],"design":[27,121,300],"features,":[28],"some":[29],"which":[31,221,305,350],"lack":[32],"generality":[34],"genre":[37,100,189,272],"classification.":[38,273],"Deep":[39],"learning":[40,60],"has":[41],"had":[42],"a":[43,104,194],"large":[44],"scientific":[47],"research":[48],"results":[49],"classification,":[55,101,190],"but":[56],"existing":[58],"deep":[59],"methods":[61],"still":[62],"have":[63],"problems":[65,174],"insufficient":[67,180],"extraction":[68,226],"feature":[71,181,225],"information,":[72,83,179],"low":[73,184],"accuracy":[74,97,133,186,280,340,356],"rate":[75],"genres,":[78],"loss":[79,176],"time":[81,136,178,323],"series":[82],"slow":[85],"training.":[86],"To":[87],"address":[88],"problem":[90],"that":[91,197,338],"durations":[94,127],"affect":[95],"we":[102,120,192,284],"form":[103],"Log":[105,158,252],"Mel":[106,159,166,253],"spectrum":[107,160],"with":[108,124,202,295,358],"audio":[110,144],"data":[111,122],"cut":[114],"durations.":[115],"After":[116],"discarding":[117],"incomplete":[118],"audio,":[119],"enhancement":[123],"slicing":[126],"verify":[129],"its":[130],"effect":[131],"on":[132,141,290,346],"training":[135],"through":[137],"comparison":[138],"experiments.":[139],"Based":[140],"this,":[142],"signal":[145],"divided":[147],"into":[148,266],"frames,":[149],"windowed":[150],"short-time":[152],"Fourier":[153],"transformed,":[154],"then":[156],"obtained":[162],"using":[164],"filter":[167],"logarithmic":[169],"compression.":[170],"Aiming":[171],"at":[172],"extraction,":[182],"firstly,":[191],"propose":[193,285],"Res-Transformer":[195,292],"model":[196,208,288],"fuses":[198],"residual":[200,219],"network":[201,229],"Transformer":[204,242],"coding":[205,243],"layer.":[206],"consists":[209],"two":[211,260,320],"branches,":[212],"left":[214],"branch":[215,239],"an":[217,352],"improved":[218],"network,":[220],"enhances":[222],"spectral":[224],"ability":[227,231],"expression":[230],"realizes":[233],"dimensionality":[235],"reduction;":[236],"right":[238],"uses":[240],"four":[241],"layers":[244],"extract":[246,313],"time-series":[248],"information":[249],"spectrum.":[254],"output":[256],"vectors":[257],"branches":[261],"are":[262],"spliced":[263],"input":[265,328],"classifier":[268],"realize":[270],"Then,":[274],"further":[276],"improve":[277],"model,":[283,293],"TS-Resformer":[287],"based":[289],"combined":[294],"attention":[297,303,332],"mechanisms,":[298],"time-frequency":[302,331],"mechanism,":[304,333],"employs":[306],"scales":[308],"filters":[310],"fully":[312],"low-level":[315],"features":[317],"from":[318],"dimensions":[321],"frequency":[325],"as":[326],"respectively.":[334],"Finally,":[335],"experiments":[336],"show":[337],"this":[342],"method":[343],"90.23%":[345],"FMA-small":[348],"dataset,":[349],"improvement":[353],"compared":[357],"classical":[360],"model.":[361]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}