{"id":"https://openalex.org/W4416249863","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228274","title":"Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generation","display_name":"Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249863","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228274"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5018900146","display_name":"J. Zhang","orcid":"https://orcid.org/0000-0002-5005-6972"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jincheng Zhang","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032485940","display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gy\u00f6rgy Fazekas","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083980012","display_name":"Charalampos Saitis","orcid":"https://orcid.org/0000-0002-6860-9723"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Charalampos Saitis","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018900146"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":2.8193,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92391731,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.7925000190734863,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.7925000190734863,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.14830000698566437,"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/T12290","display_name":"Human Motion and Animation","score":0.007499999832361937,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/the-symbolic","display_name":"The Symbolic","score":0.6991000175476074},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5705000162124634},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4853000044822693},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4555000066757202},{"id":"https://openalex.org/keywords/symbolic-trajectory-evaluation","display_name":"Symbolic trajectory evaluation","score":0.4487999975681305},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.34130001068115234},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3192000091075897}],"concepts":[{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.6991000175476074},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.588100016117096},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4555000066757202},{"id":"https://openalex.org/C23123167","wikidata":"https://www.wikidata.org/wiki/Q7661193","display_name":"Symbolic trajectory evaluation","level":3,"score":0.4487999975681305},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44519999623298645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.415800005197525},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3749000132083893},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3165999948978424},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C65620979","wikidata":"https://www.wikidata.org/wiki/Q7661176","display_name":"Symbolic data analysis","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C149227320","wikidata":"https://www.wikidata.org/wiki/Q884718","display_name":"Block diagram","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2194775991","https://openalex.org/W4225570023","https://openalex.org/W4312938066","https://openalex.org/W4385567278","https://openalex.org/W4386066464","https://openalex.org/W4402671601","https://openalex.org/W4402716142","https://openalex.org/W4404037676"],"related_works":[],"abstract_inverted_index":{"The":[0],"recent":[1],"surge":[2],"in":[3,22,113,124],"the":[4,64,70,121],"popularity":[5],"of":[6,43,66,72,115],"diffusion":[7,48,67,81],"models":[8,49,68],"for":[9,19,53,69],"image":[10],"synthesis":[11],"has":[12],"attracted":[13],"new":[14],"attention":[15],"to":[16,28,97],"their":[17,26],"potential":[18],"generation":[20,31,71],"tasks":[21],"other":[23],"domains.":[24],"However,":[25],"applications":[27],"symbolic":[29,36,58,73,99],"music":[30,37,59,100,116],"remain":[32],"largely":[33],"under-explored":[34],"because":[35],"is":[38,95,129],"typically":[39],"represented":[40],"as":[41,60],"sequences":[42],"discrete":[44,54],"events":[45],"and":[46,89,118],"standard":[47],"are":[50],"not":[51],"well-suited":[52],"data.":[55],"We":[56],"represent":[57],"image-like":[61],"pianorolls,":[62],"facilitating":[63],"use":[65],"music.":[74],"Moreover,":[75],"this":[76],"study":[77],"introduces":[78],"a":[79],"novel":[80],"model":[82],"that":[83,107],"incorporates":[84],"our":[85,108],"proposed":[86],"Transformer-Mamba":[87],"block":[88],"learnable":[90],"wavelet":[91],"transform.":[92],"Classifier-free":[93],"guidance":[94],"utilised":[96],"generate":[98],"with":[101],"target":[102],"chords.":[103],"Our":[104,127],"evaluation":[105],"shows":[106],"method":[109],"achieves":[110],"compelling":[111],"results":[112],"terms":[114],"quality":[117],"controllability,":[119],"outperforming":[120],"strong":[122],"baseline":[123],"pianoroll":[125],"generation.":[126],"code":[128],"available":[130],"at":[131],"https://github.com/jinchengzhanggg/proffusion.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-11-14T00:00:00"}