{"id":"https://openalex.org/W4407408487","doi":"https://doi.org/10.1186/s13636-025-00397-3","title":"AI-based Chinese-style music generation from video content: a study on cross-modal analysis and generation methods","display_name":"AI-based Chinese-style music generation from video content: a study on cross-modal analysis and generation methods","publication_year":2025,"publication_date":"2025-02-12","ids":{"openalex":"https://openalex.org/W4407408487","doi":"https://doi.org/10.1186/s13636-025-00397-3"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00397-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00397-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00397-3","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/s13636-025-00397-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Moxi Cao","raw_affiliation_strings":["Department of Global Cultural Convergence, Kangwon National University, Kangwon National University, Chuncheon, 24503, Gangwon-do, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Global Cultural Convergence, Kangwon National University, Kangwon National University, Chuncheon, 24503, Gangwon-do, South Korea","institution_ids":["https://openalex.org/I165507594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101197304","display_name":"Jiaxiang Zheng","orcid":"https://orcid.org/0009-0009-4881-4672"},"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":"Jiaxiang Zheng","raw_affiliation_strings":["Department of Global Cultural Convergence, Kangwon National University, Kangwon National University, Chuncheon, 24503, Gangwon-do, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Global Cultural Convergence, Kangwon National University, Kangwon National University, Chuncheon, 24503, 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, Nanjing, 210008, 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, Nanjing, 210008, Jiangsu, China","institution_ids":["https://openalex.org/I4210138978"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050958406"],"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":12.3118,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98917926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9961000084877014,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.892564058303833},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.674866259098053},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5977961421012878},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5008907318115234},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4332844316959381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4240034222602844},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.07578656077384949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.892564058303833},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.674866259098053},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5977961421012878},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5008907318115234},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4332844316959381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4240034222602844},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.07578656077384949},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00397-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00397-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00397-3","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:207b0f9e67b8427c8cbc00c37f742cca","is_oa":true,"landing_page_url":"https://doaj.org/article/207b0f9e67b8427c8cbc00c37f742cca","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 1-23 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00397-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00397-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00397-3","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":[],"funders":[{"id":"https://openalex.org/F4320321248","display_name":"Kangwon National University","ror":"https://ror.org/01mh5ph17"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407408487.pdf","grobid_xml":"https://content.openalex.org/works/W4407408487.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W308103137","https://openalex.org/W595324828","https://openalex.org/W1655514788","https://openalex.org/W1965555277","https://openalex.org/W2028880259","https://openalex.org/W2038121453","https://openalex.org/W2078118823","https://openalex.org/W2142222447","https://openalex.org/W2144198023","https://openalex.org/W2144343387","https://openalex.org/W2160109669","https://openalex.org/W2494515766","https://openalex.org/W2585824449","https://openalex.org/W2800976201","https://openalex.org/W2963807156","https://openalex.org/W2964345931","https://openalex.org/W2975076716","https://openalex.org/W3015523571","https://openalex.org/W3016096605","https://openalex.org/W3035626590","https://openalex.org/W3108240585","https://openalex.org/W3159771761","https://openalex.org/W3207290297","https://openalex.org/W4214614183","https://openalex.org/W4238215782","https://openalex.org/W4241129224","https://openalex.org/W4296252852","https://openalex.org/W4296693672","https://openalex.org/W4372260310","https://openalex.org/W4382142171","https://openalex.org/W4385245566","https://openalex.org/W4388254066","https://openalex.org/W4389322778","https://openalex.org/W4390873340","https://openalex.org/W4392647990","https://openalex.org/W4392904237","https://openalex.org/W6600037600","https://openalex.org/W6600339963","https://openalex.org/W6601053007","https://openalex.org/W6601851198","https://openalex.org/W6603592625","https://openalex.org/W6761046389","https://openalex.org/W6827353395"],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W2349768204","https://openalex.org/W4313326281","https://openalex.org/W574867512","https://openalex.org/W2387271333","https://openalex.org/W4250539519","https://openalex.org/W581389233","https://openalex.org/W2361120309","https://openalex.org/W632157940","https://openalex.org/W2356684049"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Artificial":[3],"Intelligence":[4],"Generated":[5],"Content":[6],"(AIGC)":[7],"technologies":[8],"have":[9,33],"advanced":[10],"rapidly,":[11],"with":[12],"models":[13,100],"such":[14],"as":[15],"Stable":[16],"Diffusion":[17,73,77],"and":[18,76,93,109,148,167],"GPT":[19],"garnering":[20],"significant":[21,36],"attention":[22],"across":[23],"various":[24],"domains.":[25],"Against":[26],"this":[27,57,59],"backdrop,":[28],"AI-driven":[29],"music":[30,50,66,89,137,153],"composition":[31],"techniques":[32],"also":[34,140],"produced":[35],"progress.":[37],"However,":[38],"no":[39],"existing":[40],"model":[41,68,86,117],"has":[42],"yet":[43],"demonstrated":[44],"the":[45,71,84,98,116,119,130,150,156,165,174],"capability":[46],"to":[47,52,97,146],"generate":[48],"Chinese-style":[49,53,64,88,91],"corresponding":[51],"videos.":[54],"To":[55],"address":[56],"gap,":[58],"study":[60],"proposes":[61],"a":[62,142],"novel":[63],"video":[65],"generation":[67],"based":[69],"on":[70],"Latent":[72],"Model":[74],"(LDM)":[75],"Transformers":[78],"(DiT).":[79],"Experimental":[80],"results":[81],"demonstrate":[82],"that":[83,115],"proposed":[85],"generates":[87],"from":[90],"videos":[92],"achieves":[94],"performance":[95],"comparable":[96],"baseline":[99],"in":[101,136,155,173],"audio":[102],"quality,":[103],"distribution":[104],"fitting,":[105],"musicality,":[106],"rhythmic":[107],"stability,":[108],"audio-visual":[110],"synchronization.":[111],"These":[112],"findings":[113],"indicate":[114],"captures":[118],"stylistic":[120],"features":[121],"of":[122,133,169],"Chinese":[123,152,170],"music.":[124],"This":[125],"research":[126],"not":[127],"only":[128],"demonstrates":[129],"feasibility":[131],"applications":[132],"artificial":[134],"intelligence":[135],"creation":[138],"but":[139],"provides":[141],"new":[143,162],"technological":[144],"approach":[145],"preserve":[147],"innovate":[149],"traditional":[151],"culture":[154],"digital":[157,175],"era.":[158],"Furthermore,":[159],"it":[160],"explores":[161],"possibilities":[163],"for":[164],"dissemination":[166],"innovation":[168],"cultural":[171],"arts":[172],"age.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
