{"id":"https://openalex.org/W4415584170","doi":"https://doi.org/10.1186/s13636-025-00423-4","title":"Chinese instrument music source separation with frequency-attentive multi-band neural networks","display_name":"Chinese instrument music source separation with frequency-attentive multi-band neural networks","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415584170","doi":"https://doi.org/10.1186/s13636-025-00423-4"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00423-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00423-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00423-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00423-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087251080","display_name":"Jiaxiang Zheng","orcid":"https://orcid.org/0009-0000-1407-8894"},"institutions":[{"id":"https://openalex.org/I165507594","display_name":"Kangwon National University","ror":"https://ror.org/01mh5ph17","country_code":"KR","type":"education","lineage":["https://openalex.org/I165507594"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jiaxiang Zheng","raw_affiliation_strings":["Department of Global Cultural Convergence, Kangwon National University, Kangwon National University, 24503, Chuncheon, Gangwon-do, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Global Cultural Convergence, Kangwon National University, Kangwon National University, 24503, Chuncheon, Gangwon-do, South Korea","institution_ids":["https://openalex.org/I165507594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050958406","display_name":"Moxi Cao","orcid":"https://orcid.org/0009-0000-2769-2316"},"institutions":[{"id":"https://openalex.org/I165507594","display_name":"Kangwon National University","ror":"https://ror.org/01mh5ph17","country_code":"KR","type":"education","lineage":["https://openalex.org/I165507594"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Moxi Cao","raw_affiliation_strings":["Department of Global Cultural Convergence, Kangwon National University, Kangwon National University, 24503, Chuncheon, Gangwon-do, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Global Cultural Convergence, Kangwon National University, Kangwon National University, 24503, Chuncheon, Gangwon-do, South Korea","institution_ids":["https://openalex.org/I165507594"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019983629","display_name":"Chongbin Zhang","orcid":"https://orcid.org/0009-0004-5214-9840"},"institutions":[{"id":"https://openalex.org/I4210138978","display_name":"Nanjing University of the Arts","ror":"https://ror.org/0457pxg28","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210138978"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongbin Zhang","raw_affiliation_strings":["School of Modern Music and Technology, Nanjing University of the Arts, Beijing West Road, 210008, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0004-5214-9840","affiliations":[{"raw_affiliation_string":"School of Modern Music and Technology, Nanjing University of the Arts, Beijing West Road, 210008, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I4210138978"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087251080"],"corresponding_institution_ids":["https://openalex.org/I165507594"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.2312,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84029196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9915000200271606,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.8359000086784363},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5938000082969666},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5426999926567078},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5236999988555908},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.41920000314712524},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.415800005197525},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.388700008392334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8654000163078308},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.8359000086784363},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5426999926567078},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.519599974155426},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.415800005197525},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.388700008392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C2778116611","wikidata":"https://www.wikidata.org/wiki/Q25110567","display_name":"Frequency band","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00423-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00423-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00423-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1e831ce078904a6f88d9a0666fe85608","is_oa":true,"landing_page_url":"https://doaj.org/article/1e831ce078904a6f88d9a0666fe85608","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":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-24 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00423-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00423-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00423-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7476887950","display_name":null,"funder_award_id":"24BH170","funder_id":"https://openalex.org/F4320335869","funder_display_name":"National Social Science Fund of China"}],"funders":[{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null},{"id":"https://openalex.org/F4320337368","display_name":"Division of Graduate Education","ror":"https://ror.org/00whkrf32"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415584170.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W165956390","https://openalex.org/W1902027874","https://openalex.org/W2003988342","https://openalex.org/W2079735306","https://openalex.org/W2105892554","https://openalex.org/W2124539664","https://openalex.org/W2127851351","https://openalex.org/W2607288499","https://openalex.org/W2895583029","https://openalex.org/W2899579490","https://openalex.org/W2915016266","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963992487","https://openalex.org/W2964070952","https://openalex.org/W2972411915","https://openalex.org/W2998490864","https://openalex.org/W3016005489","https://openalex.org/W3037149862","https://openalex.org/W3095999710","https://openalex.org/W3160050861","https://openalex.org/W3162893611","https://openalex.org/W3199957557","https://openalex.org/W3212314443","https://openalex.org/W4225261970","https://openalex.org/W4391790195","https://openalex.org/W4392909836","https://openalex.org/W4401609562"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,44,122,165],"music":[3,109,145,169],"source":[4,110,146,186],"separation":[5,45,111,147,167],"has":[6],"been":[7],"accelerated":[8],"by":[9],"deep":[10,51],"learning":[11,52],"techniques,":[12,39],"yet":[13],"most":[14],"studies":[15],"have":[16],"focused":[17],"on":[18,88],"Western":[19],"instruments":[20,31],"and":[21,36,77,97,103,171,178,188,196],"vocals,":[22],"with":[23,100,115,126,132],"limited":[24],"attention":[25,102,105],"to":[26,57,61,107],"traditional":[27,63,181],"Chinese":[28,64],"instruments.":[29],"These":[30,156],"possess":[32],"distinctive":[33],"timbral":[34],"characteristics":[35],"complex":[37],"performance":[38],"which":[40],"require":[41],"specialized":[42],"treatment":[43],"tasks.":[46],"This":[47],"paper":[48],"introduces":[49],"a":[50],"approach":[53],"that":[54,139],"is":[55],"tuned":[56],"the":[58,69,79,140,159,166,176],"frequency":[59,83,101,128],"band":[60,84],"separate":[62],"instrument":[65],"sources.":[66],"By":[67],"analyzing":[68],"spectral":[70,134,154],"energy":[71],"distributions":[72],"of":[73,161,168,180],"guzheng,":[74],"dizi,":[75],"pipa,":[76],"xiao,":[78],"model":[80,184],"adopts":[81],"differentiated":[82],"processing":[85],"strategies":[86],"based":[87],"each":[89],"instrument\u2019s":[90],"acoustic":[91],"profile.":[92],"The":[93,136],"architecture":[94],"integrates":[95],"convolutional":[96],"recurrent":[98],"modules":[99],"multi-head":[104],"mechanisms":[106],"enhance":[108],"performance.":[112],"Extensive":[113],"experiments":[114],"13":[116],"band-division":[117],"configurations":[118],"reveal":[119],"significant":[120],"variations":[121],"sensitivity":[123],"across":[124],"instruments,":[125],"optimal":[127],"splits":[129],"aligning":[130],"closely":[131],"their":[133],"characteristics.":[135],"results":[137],"demonstrate":[138],"proposed":[141],"method":[142],"achieves":[143],"high-quality":[144],"while":[148],"reducing":[149],"computational":[150],"costs":[151],"through":[152],"adaptive":[153],"processing.":[155],"findings":[157],"highlight":[158],"importance":[160],"culturally":[162],"informed":[163],"modeling":[164],"sources":[170],"open":[172],"new":[173],"directions":[174],"for":[175],"preservation":[177],"analysis":[179],"music.":[182],"All":[183],"weights,":[185],"code,":[187],"audio":[189],"demonstrations":[190],"are":[191],"publicly":[192],"available":[193],"at":[194],"https://huggingface.co/NMLAB8/CISM":[195],"https://huggingface.co/spaces/NMLAB8/CISM":[197],".":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-28T00:00:00"}