{"id":"https://openalex.org/W4411580985","doi":"https://doi.org/10.3390/signals6030030","title":"Multi-Instance Multi-Scale Graph Attention Neural Net with Label Semantic Embeddings for Instrument Recognition","display_name":"Multi-Instance Multi-Scale Graph Attention Neural Net with Label Semantic Embeddings for Instrument Recognition","publication_year":2025,"publication_date":"2025-06-24","ids":{"openalex":"https://openalex.org/W4411580985","doi":"https://doi.org/10.3390/signals6030030"},"language":"en","primary_location":{"id":"doi:10.3390/signals6030030","doi":"https://doi.org/10.3390/signals6030030","is_oa":true,"landing_page_url":"https://doi.org/10.3390/signals6030030","pdf_url":"https://www.mdpi.com/2624-6120/6/3/30/pdf?version=1750769080","source":{"id":"https://openalex.org/S4210225709","display_name":"Signals","issn_l":"2624-6120","issn":["2624-6120"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signals","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2624-6120/6/3/30/pdf?version=1750769080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103086538","display_name":"Na Bai","orcid":"https://orcid.org/0009-0003-3893-4861","observed_orcids":["https://orcid.org/0009-0003-3893-4861"]},"institutions":[{"id":"https://openalex.org/I4210105569","display_name":"Jiangsu Vocational Institute of Architectural Technology","ror":"https://ror.org/01d4y8v03","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105569"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Bai","raw_affiliation_strings":["College of Information and Electrical Engineering, Jiangsu Vocational Institute of Architectural Technology, Xuzhou 221116, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Electrical Engineering, Jiangsu Vocational Institute of Architectural Technology, Xuzhou 221116, China","institution_ids":["https://openalex.org/I4210105569"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023749072","display_name":"Zhaoli Wu","orcid":"https://orcid.org/0000-0002-2907-4703","observed_orcids":["https://orcid.org/0000-0002-2907-4703"]},"institutions":[{"id":"https://openalex.org/I4210105569","display_name":"Jiangsu Vocational Institute of Architectural Technology","ror":"https://ror.org/01d4y8v03","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210105569"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoli Wu","raw_affiliation_strings":["College of Information and Electrical Engineering, Jiangsu Vocational Institute of Architectural Technology, Xuzhou 221116, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Electrical Engineering, Jiangsu Vocational Institute of Architectural Technology, Xuzhou 221116, China","institution_ids":["https://openalex.org/I4210105569"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749320","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0003-4995-6495","observed_orcids":["https://orcid.org/0000-0003-4995-6495","https://orcid.org/0000-0002-5708-3578"]},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023749072","https://openalex.org/A5100749320"],"corresponding_institution_ids":["https://openalex.org/I25757504","https://openalex.org/I4210105569"],"apc_list":{"value":1000,"currency":"CHF","value_usd":1207},"apc_paid":{"value":1000,"currency":"CHF","value_usd":1207},"fwci":0.4984,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60254027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"6","issue":"3","first_page":"30","last_page":"30"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.0,"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/musical-instrument-recognition","display_name":"instrument identification","score":0.9580000042915344},{"id":"https://openalex.org/keywords/multiple-instance-learning","display_name":"multiple instance learning","score":0.7639999985694885},{"id":"https://openalex.org/keywords/multiscale-feature-extraction","display_name":"multi-scale feature extraction","score":0.578000009059906},{"id":"https://openalex.org/keywords/polyphony","display_name":"polyphony","score":0.8149999976158142},{"id":"https://openalex.org/keywords/timbre-similarity","display_name":"timbre similarity","score":0.8259999752044678},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"music information retrieval","score":0.6959999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.624341607093811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5211330056190491},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5200300216674805},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46023228764533997},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4516136944293976},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4218599796295166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3459651470184326},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26331108808517456},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0711771547794342},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/signals6030030","doi":"https://doi.org/10.3390/signals6030030","is_oa":true,"landing_page_url":"https://doi.org/10.3390/signals6030030","pdf_url":"https://www.mdpi.com/2624-6120/6/3/30/pdf?version=1750769080","source":{"id":"https://openalex.org/S4210225709","display_name":"Signals","issn_l":"2624-6120","issn":["2624-6120"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signals","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bafaf546458e46d69c8a4c455bf241ec","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/bafaf546458e46d69c8a4c455bf241ec","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,"listed_in":[],"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":"Signals, Vol 6, Iss 3, p 30 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/signals6030030","doi":"https://doi.org/10.3390/signals6030030","is_oa":true,"landing_page_url":"https://doi.org/10.3390/signals6030030","pdf_url":"https://www.mdpi.com/2624-6120/6/3/30/pdf?version=1750769080","source":{"id":"https://openalex.org/S4210225709","display_name":"Signals","issn_l":"2624-6120","issn":["2624-6120"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","norway-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signals","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6191981406","display_name":null,"funder_award_id":"62206297","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411580985.pdf","grobid_xml":"https://content.openalex.org/works/W4411580985.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1590102137","https://openalex.org/W1978467019","https://openalex.org/W2029002095","https://openalex.org/W2062898807","https://openalex.org/W2096623359","https://openalex.org/W2164877274","https://openalex.org/W2166693890","https://openalex.org/W2395945925","https://openalex.org/W2407127962","https://openalex.org/W2410860376","https://openalex.org/W2899260162","https://openalex.org/W2903137797","https://openalex.org/W2903539539","https://openalex.org/W2962866211","https://openalex.org/W2990912900","https://openalex.org/W3004440566","https://openalex.org/W3082851515","https://openalex.org/W3098670224","https://openalex.org/W3169905056","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W4280618035","https://openalex.org/W4288779867","https://openalex.org/W4313050943","https://openalex.org/W4317207486","https://openalex.org/W4362604731","https://openalex.org/W4386601513","https://openalex.org/W4399929809","https://openalex.org/W4401612797","https://openalex.org/W4401691959","https://openalex.org/W6851997739"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W4205958290","https://openalex.org/W4384212932","https://openalex.org/W4390590544","https://openalex.org/W2096195258","https://openalex.org/W2990460313","https://openalex.org/W2973458857"],"abstract_inverted_index":{"Instrument":[0],"recognition":[1,129,262,275],"is":[2,48,252],"a":[3,135],"crucial":[4],"aspect":[5],"of":[6,52,60,76,110,118,164,172,180,185,199,217,250],"music":[7,37],"information":[8,195],"retrieval,":[9],"and":[10,43,64,160,188,204,244,256],"in":[11,41,57,80,273],"recent":[12],"years,":[13],"machine":[14],"learning-based":[15],"methods":[16],"have":[17],"become":[18],"the":[19,50,61,77,94,108,116,158,170,178,183,197,208,215,240],"primary":[20],"approach":[21],"to":[22,31,90,156,176,234,258],"addressing":[23],"this":[24,132],"challenge.":[25],"However,":[26],"existing":[27,271],"models":[28],"often":[29,70,86],"struggle":[30],"accurately":[32],"identify":[33],"multiple":[34,83],"instruments":[35,51,84,105,165,187,201,237],"within":[36],"tracks":[38],"that":[39,49,268],"vary":[40],"length":[42],"quality.":[44],"One":[45],"key":[46],"issue":[47],"interest":[53],"may":[54],"not":[55],"appear":[56],"every":[58],"clip":[59],"audio":[62,97,210,218],"sample,":[63],"when":[65],"they":[66,68],"do,":[67],"are":[69,85],"unevenly":[71],"distributed":[72],"across":[73],"different":[74,104,167,186,200,236],"sections":[75],"track.":[78],"Additionally,":[79],"polyphonic":[81],"music,":[82],"played":[87],"simultaneously,":[88],"leading":[89],"signal":[91,211],"overlap.":[92],"Using":[93],"same":[95],"overlapping":[96,209],"signals":[98,181],"as":[99,202],"partial":[100],"classification":[101,190],"features":[102,111,219],"for":[103,126,147,220],"will":[106],"reduce":[107],"distinguishability":[109,179],"between":[112],"instruments,":[113],"thereby":[114,213],"affecting":[115],"performance":[117],"instrument":[119,128,148,261,274],"recognition.":[120,149],"These":[121],"complexities":[122],"present":[123],"significant":[124],"challenges":[125],"current":[127],"models.":[130,263],"Therefore,":[131],"paper":[133],"proposes":[134],"multi-instance":[136,173,228],"multi-scale":[137,229],"graph":[138,155,230],"attention":[139,231],"neural":[140,232],"network":[141,233],"(MMGAT)":[142],"with":[143],"label":[144,245],"semantic":[145,194,246],"embeddings":[146,203],"MMGAT":[150,192,223,251,269],"designs":[151,225],"an":[152,226],"instance":[153,241],"correlation":[154,242],"model":[157],"presence":[159],"quantitative":[161],"timbre":[162],"similarity":[163],"at":[166],"positions":[168],"from":[169,196],"perspective":[171],"learning.":[174],"Then,":[175],"enhance":[177],"after":[182],"overlap":[184],"improve":[189],"accuracy,":[191],"learns":[193],"labels":[198],"incorporates":[205],"them":[206],"into":[207],"features,":[212],"enhancing":[214],"differentiability":[216],"various":[221],"instruments.":[222],"then":[224],"instance-based":[227],"recognize":[235],"based":[238],"on":[239],"graphs":[243],"embeddings.":[247],"The":[248,264],"effectiveness":[249],"validated":[253],"through":[254],"experiments":[255],"compared":[257],"commonly":[259],"used":[260],"experimental":[265],"results":[266],"demonstrate":[267],"outperforms":[270],"approaches":[272],"tasks.":[276]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2025-10-10T00:00:00"}