{"id":"https://openalex.org/W4408354807","doi":"https://doi.org/10.1109/icassp49660.2025.10888635","title":"Melody Structure Transfer Network: Generating Music with Separable Self-Attention","display_name":"Melody Structure Transfer Network: Generating Music with Separable Self-Attention","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354807","doi":"https://doi.org/10.1109/icassp49660.2025.10888635"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5056913693","display_name":"Junlin Wu","orcid":"https://orcid.org/0009-0006-1037-1827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junlin Wu","raw_affiliation_strings":["MOE Key Lab of AI,Dept. of CSE,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Lab of AI,Dept. of CSE,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762509","display_name":"Ning Zhang","orcid":"https://orcid.org/0000-0003-0399-5085"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Zhang","raw_affiliation_strings":["MOE Key Lab of AI,Dept. of CSE,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Lab of AI,Dept. of CSE,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100616103","display_name":"Cheng Zhong","orcid":"https://orcid.org/0000-0003-1852-5860"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Zhong","raw_affiliation_strings":["MOE Key Lab of AI,Dept. of CSE,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Lab of AI,Dept. of CSE,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071650569","display_name":"Boan Chen","orcid":"https://orcid.org/0000-0003-4484-3416"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,School of AI,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of AI,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012653602","display_name":"Huanxi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huanxi Liu","raw_affiliation_strings":["MOE Key Lab of AI,Dept. of CSE,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MOE Key Lab of AI,Dept. of CSE,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087158377","display_name":"Junchi Yan","orcid":"https://orcid.org/0000-0001-9639-7679"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchi Yan","raw_affiliation_strings":["Shanghai Jiao Tong University,School of AI,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of AI,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9925000071525574,"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":0.9546999931335449,"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":0.6881983280181885},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.5342124700546265},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.47501882910728455},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45219123363494873},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14415568113327026},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.13268083333969116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6881983280181885},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.5342124700546265},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.47501882910728455},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45219123363494873},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14415568113327026},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.13268083333969116},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2101642281","https://openalex.org/W2125819366","https://openalex.org/W2579406683","https://openalex.org/W2775487773","https://openalex.org/W2982753834","https://openalex.org/W3035376600","https://openalex.org/W3092879656","https://openalex.org/W4210892268","https://openalex.org/W4312576456","https://openalex.org/W4385245566","https://openalex.org/W4391870567","https://openalex.org/W4402774235","https://openalex.org/W6704583309","https://openalex.org/W6756207296","https://openalex.org/W6760601182","https://openalex.org/W6768028577","https://openalex.org/W6802346438","https://openalex.org/W6854368142"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2009525028","https://openalex.org/W2390279801","https://openalex.org/W4321064619","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Most":[0],"existing":[1],"symbolic":[2],"music":[3,24,76,107],"generation":[4],"methods":[5],"focus":[6],"on":[7],"generating":[8,56],"short":[9],"pieces,":[10],"typically":[11],"less":[12],"than":[13],"8":[14],"bars":[15],"and":[16,68,93],"occasionally":[17],"up":[18,79],"to":[19,47,80,105],"32":[20],"bars.":[21],"Generating":[22],"long":[23],"sequences":[25,77],"requires":[26],"effective":[27],"representation":[28],"of":[29,52,70,78,96],"coherent":[30],"musical":[31,41],"structures.":[32,42],"Vanilla":[33],"self-attention":[34],"face":[35],"challenges":[36],"in":[37],"capturing":[38],"subtle":[39],"long-term":[40],"We":[43,58],"propose":[44],"an":[45],"approach":[46],"transfer":[48,69],"the":[49,66,91,97,102],"structural":[50,71,92],"characteristics":[51],"training":[53,98],"samples":[54],"for":[55],"music.":[57],"introduce":[59],"a":[60],"separable":[61],"self-attention-based":[62],"model":[63],"that":[64,88],"facilitates":[65],"learning":[67],"embeddings.":[72],"It":[73],"can":[74],"generate":[75,106],"100":[81],"bars,":[82],"producing":[83],"compositions":[84],"with":[85,108],"interpretable":[86],"structures":[87,110],"closely":[89],"resemble":[90],"compositional":[94],"techniques":[95],"set.":[99],"Experiments":[100],"show":[101],"model\u2019s":[103],"ability":[104],"targeted":[109],"while":[111],"maintaining":[112],"good":[113],"diversity.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}