{"id":"https://openalex.org/W4414798820","doi":"https://doi.org/10.1109/access.2025.3617184","title":"StructMamba: Structured Harmonic and Temporal Music Analysis via Dual-Axis Mamba and Attention","display_name":"StructMamba: Structured Harmonic and Temporal Music Analysis via Dual-Axis Mamba and Attention","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414798820","doi":"https://doi.org/10.1109/access.2025.3617184"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3617184","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3617184","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3617184","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010061205","display_name":"Amit Kumar Bairwa","orcid":"https://orcid.org/0000-0003-1830-0661"},"institutions":[{"id":"https://openalex.org/I73779912","display_name":"Manipal University Jaipur","ror":"https://ror.org/040h76494","country_code":null,"type":"education","lineage":["https://openalex.org/I73779912"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amit Kumar Bairwa","raw_affiliation_strings":["School of Computer Science and Engineering, Manipal University Jaipur, Jaipur, India","School of Computer Science and Engineering, Manipal University Jaipur, Jaipur-Ajmer Express Highway, Jaipur, India"],"raw_orcid":"https://orcid.org/0000-0003-1830-0661","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Manipal University Jaipur, Jaipur, India","institution_ids":["https://openalex.org/I73779912"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Manipal University Jaipur, Jaipur-Ajmer Express Highway, Jaipur, India","institution_ids":["https://openalex.org/I73779912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137165","display_name":"Siddhanth Bhat","orcid":"https://orcid.org/0009-0005-6350-6601"},"institutions":[{"id":"https://openalex.org/I73779912","display_name":"Manipal University Jaipur","ror":"https://ror.org/040h76494","country_code":null,"type":"education","lineage":["https://openalex.org/I73779912"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Siddhanth Bhat","raw_affiliation_strings":["School of Computer Science and Engineering, Manipal University Jaipur, Jaipur, India","School of Computer Science and Engineering, Manipal University Jaipur, Jaipur-Ajmer Express Highway, Jaipur, India"],"raw_orcid":"https://orcid.org/0009-0005-6350-6601","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Manipal University Jaipur, Jaipur, India","institution_ids":["https://openalex.org/I73779912"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Manipal University Jaipur, Jaipur-Ajmer Express Highway, Jaipur, India","institution_ids":["https://openalex.org/I73779912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107676497","display_name":"Tanishk Sawant","orcid":"https://orcid.org/0009-0000-4597-8721"},"institutions":[{"id":"https://openalex.org/I73779912","display_name":"Manipal University Jaipur","ror":"https://ror.org/040h76494","country_code":null,"type":"education","lineage":["https://openalex.org/I73779912"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanishk Sawant","raw_affiliation_strings":["School of Computer Science and Engineering, Manipal University Jaipur, Jaipur, India","School of Computer Science and Engineering, Manipal University Jaipur, Jaipur-Ajmer Express Highway, Jaipur, India"],"raw_orcid":"https://orcid.org/0009-0000-4597-8721","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Manipal University Jaipur, Jaipur, India","institution_ids":["https://openalex.org/I73779912"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Manipal University Jaipur, Jaipur-Ajmer Express Highway, Jaipur, India","institution_ids":["https://openalex.org/I73779912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060928193","display_name":"Manoj Kumar Bohra","orcid":"https://orcid.org/0000-0002-2727-5106"},"institutions":[{"id":"https://openalex.org/I73779912","display_name":"Manipal University Jaipur","ror":"https://ror.org/040h76494","country_code":null,"type":"education","lineage":["https://openalex.org/I73779912"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manoj Kumar Bohra","raw_affiliation_strings":["School of Computer Science and Engineering, Manipal University Jaipur, Jaipur, India","School of Computer Science and Engineering, Manipal University Jaipur, Jaipur-Ajmer Express Highway, Jaipur, India"],"raw_orcid":"https://orcid.org/0000-0002-2727-5106","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Manipal University Jaipur, Jaipur, India","institution_ids":["https://openalex.org/I73779912"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Manipal University Jaipur, Jaipur-Ajmer Express Highway, Jaipur, India","institution_ids":["https://openalex.org/I73779912"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73779912"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29977846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"186435","last_page":"186448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.9965999722480774,"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":0.993399977684021,"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":0.9449999928474426,"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/spectrogram","display_name":"Spectrogram","score":0.8695999979972839},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.733299970626831},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5070000290870667},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4449000060558319},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.4426000118255615},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4374000132083893},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.413100004196167},{"id":"https://openalex.org/keywords/harmonic-analysis","display_name":"Harmonic analysis","score":0.40299999713897705},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.39649999141693115}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8695999979972839},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.733299970626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715499997138977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.535099983215332},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4449000060558319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C131770355","wikidata":"https://www.wikidata.org/wiki/Q876215","display_name":"Harmonic analysis","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.38029998540878296},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3614000082015991},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3001999855041504},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C178884764","wikidata":"https://www.wikidata.org/wiki/Q510293","display_name":"Musical acoustics","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C171342078","wikidata":"https://www.wikidata.org/wiki/Q4231865","display_name":"Conceptual blending","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C558987187","wikidata":"https://www.wikidata.org/wiki/Q1544924","display_name":"Musical analysis","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3617184","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3617184","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2cfde5d20d0e49138d96512487968811","is_oa":true,"landing_page_url":"https://doaj.org/article/2cfde5d20d0e49138d96512487968811","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":"IEEE Access, Vol 13, Pp 186435-186448 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3617184","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3617184","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modeling":[0],"musical":[1,32],"audio":[2,123,138],"requires":[3],"capturing":[4],"hierarchical":[5],"relationships":[6],"between":[7],"harmonic":[8,66],"textures,":[9],"rhythmic":[10,68],"motifs,":[11,113],"and":[12,58,67,85,93,115,132,147],"long-range":[13],"structural":[14,86],"repetitions.":[15],"Convolutional":[16],"networks":[17],"extract":[18],"local":[19],"features":[20],"efficiently,":[21],"while":[22,96],"transformers":[23],"provide":[24],"global":[25,48],"modeling,":[26,139],"yet":[27],"both":[28],"face":[29],"mismatches":[30],"with":[31,47,108,140],"structure.":[33],"In":[34],"this":[35],"work":[36],"we":[37],"introduce":[38],"StructMamba,":[39],"a":[40],"dual-axis":[41],"architecture":[42],"that":[43],"unifies":[44],"state-space":[45],"modeling":[46,55],"two-dimensional":[49],"attention.":[50,75],"Our":[51],"design":[52],"decomposes":[53],"spectrogram":[54],"into":[56],"frequency-wise":[57],"time-wise":[59],"Mamba":[60],"modules,":[61],"enabling":[62],"independent":[63],"learning":[64],"of":[65],"dependencies":[69],"before":[70],"fusing":[71],"them":[72],"through":[73],"structured":[74],"Evaluated":[76],"on":[77],"benchmark":[78],"tasks":[79],"in":[80,99],"genre":[81],"classification,":[82],"onset":[83],"detection,":[84],"segmentation,":[87],"StructMamba":[88,128],"outperforms":[89],"strong":[90],"CNN,":[91],"transformer,":[92],"hybrid":[94],"baselines,":[95],"maintaining":[97],"stability":[98],"low-resource":[100],"settings.":[101],"Beyond":[102],"accuracy,":[103],"its":[104],"internal":[105],"representations":[106],"align":[107],"music-theoretic":[109],"constructs":[110],"such":[111],"as":[112,129],"downbeats,":[114],"sectional":[116],"boundaries,":[117],"offering":[118],"rare":[119],"interpretability":[120],"for":[121,136,143],"deep":[122],"models.":[124],"These":[125],"findings":[126],"position":[127],"an":[130],"efficient":[131],"musically":[133],"aligned":[134],"solution":[135],"time\u2013frequency":[137],"practical":[141],"implications":[142],"music":[144],"education,":[145],"annotation,":[146],"production.":[148]},"counts_by_year":[],"updated_date":"2025-11-06T23:17:08.748858","created_date":"2025-10-10T00:00:00"}
