{"id":"https://openalex.org/W4321225547","doi":"https://doi.org/10.1186/s13636-022-00267-2","title":"A latent rhythm complexity model for attribute-controlled drum pattern generation","display_name":"A latent rhythm complexity model for attribute-controlled drum pattern generation","publication_year":2023,"publication_date":"2023-02-17","ids":{"openalex":"https://openalex.org/W4321225547","doi":"https://doi.org/10.1186/s13636-022-00267-2"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-022-00267-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00267-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00267-2","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","3091-4523"],"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","license_id":"https://openalex.org/licenses/cc-by","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/s13636-022-00267-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000588289","display_name":"Alessandro Ilic Mezza","orcid":"https://orcid.org/0000-0002-9438-3190"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessandro Ilic Mezza","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0002-9438-3190","affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012574855","display_name":"Massimiliano Zanoni","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimiliano Zanoni","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051897828","display_name":"Augusto Sarti","orcid":"https://orcid.org/0000-0002-5803-1702"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Augusto Sarti","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, Piazza Leonardo da Vinci 32, 20133, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5000588289"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.7995,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67612032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2023","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":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9995999932289124,"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/autoencoder","display_name":"Autoencoder","score":0.7441333532333374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6569151282310486},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.6407910585403442},{"id":"https://openalex.org/keywords/midi","display_name":"MIDI","score":0.5618276596069336},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5100113153457642},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47906002402305603},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.45830869674682617},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4415932893753052},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.43218228220939636},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42740464210510254},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4122188687324524},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.41208624839782715},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.15567582845687866},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14795708656311035},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14700055122375488}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7441333532333374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6569151282310486},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.6407910585403442},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.5618276596069336},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5100113153457642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47906002402305603},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.45830869674682617},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4415932893753052},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.43218228220939636},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42740464210510254},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4122188687324524},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.41208624839782715},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.15567582845687866},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14795708656311035},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14700055122375488},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13636-022-00267-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00267-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00267-2","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","3091-4523"],"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","license_id":"https://openalex.org/licenses/cc-by","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:re.public.polimi.it:11311/1250198","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1250198","pdf_url":"https://re.public.polimi.it/bitstream/11311/1250198/5/11311-1250198_Mezza.pdf","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:f5508095609c4c0fa7aebc784cf538ac","is_oa":true,"landing_page_url":"https://doaj.org/article/f5508095609c4c0fa7aebc784cf538ac","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 2023, Iss 1, Pp 1-14 (2023)","raw_type":"article"},{"id":"pmh:oai:zenodo.org:109739","is_oa":true,"landing_page_url":"https://www.openaccessrepository.it/record/109739","pdf_url":null,"source":{"id":"https://openalex.org/S4306402478","display_name":"INFM-OAR (INFN Catania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210116497","host_organization_name":"Istituto Nazionale di Fisica Nucleare, Sezione di Catania","host_organization_lineage":["https://openalex.org/I4210116497"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/s13636-022-00267-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00267-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00267-2","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","3091-4523"],"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","license_id":"https://openalex.org/licenses/cc-by","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":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4321225547.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W66110438","https://openalex.org/W181426284","https://openalex.org/W391141900","https://openalex.org/W595493862","https://openalex.org/W1591945341","https://openalex.org/W1994618660","https://openalex.org/W2001394185","https://openalex.org/W2048830892","https://openalex.org/W2061495533","https://openalex.org/W2071935995","https://openalex.org/W2072170522","https://openalex.org/W2077770566","https://openalex.org/W2084724929","https://openalex.org/W2137560425","https://openalex.org/W2163922914","https://openalex.org/W2173459623","https://openalex.org/W2276309670","https://openalex.org/W2423557781","https://openalex.org/W2467897964","https://openalex.org/W2478051194","https://openalex.org/W2495489804","https://openalex.org/W2730106296","https://openalex.org/W2775487773","https://openalex.org/W2962691331","https://openalex.org/W2962850167","https://openalex.org/W2963223306","https://openalex.org/W2963253162","https://openalex.org/W2963408210","https://openalex.org/W2963470893","https://openalex.org/W2964110616","https://openalex.org/W3048062783","https://openalex.org/W3099425575","https://openalex.org/W3174344449","https://openalex.org/W4241593052","https://openalex.org/W4300914774","https://openalex.org/W6602051145","https://openalex.org/W6628637903","https://openalex.org/W6631038453","https://openalex.org/W6762931180","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4285232104","https://openalex.org/W2386555541","https://openalex.org/W4242364395","https://openalex.org/W3042962886","https://openalex.org/W2920621887","https://openalex.org/W2187442448","https://openalex.org/W2153331925","https://openalex.org/W2369521057"],"abstract_inverted_index":{"Abstract":[0],"Most":[1],"music":[2,228,232],"listeners":[3],"have":[4,18],"an":[5,136],"intuitive":[6],"understanding":[7,255],"of":[8,11,32,99,124,156,165,168,177,221,249,256,259],"the":[9,78,84,97,122,146,154,172,184,200,209,235,246],"notion":[10],"rhythm":[12,49,111],"complexity.":[13],"Musicologists":[14],"and":[15,25,82,127,180,192,199,205,230],"scientists,":[16],"however,":[17],"long":[19],"sought":[20],"objective":[21],"ways":[22],"to":[23,77,95,217],"measure":[24,51,86],"model":[26,109,213],"such":[27],"a":[28,46,67,88,106,115,162,196,218,253],"distinctively":[29],"perceptual":[30,89,257],"attribute":[31],"music.":[33,260],"Whereas":[34],"previous":[35],"research":[36],"has":[37],"mainly":[38],"focused":[39],"on":[40,73,114,161],"monophonic":[41],"patterns,":[42],"this":[43,143,212],"article":[44],"presents":[45],"novel":[47],"perceptually-informed":[48],"complexity":[50,98,112,123,155,186],"specifically":[52],"designed":[53],"for":[54,110,225],"polyphonic":[55,169],"rhythms,":[56],"i.e.,":[57],"patterns":[58],"in":[59],"which":[60],"multiple":[61],"simultaneous":[62],"voices":[63],"cooperate":[64],"toward":[65,244],"creating":[66],"coherent":[68,179],"musical":[69,80],"phrase.":[70],"We":[71],"focus":[72],"drum":[74,170],"rhythms":[75],"relating":[76],"Western":[79],"tradition":[81],"validate":[83],"proposed":[85,173],"through":[87],"test":[90],"where":[91],"users":[92],"were":[93],"asked":[94],"rate":[96],"real-life":[100],"drumming":[101],"performances.":[102],"Hence,":[103],"we":[104],"propose":[105],"latent":[107,132,147,201],"vector":[108],"based":[113],"recurrent":[116],"variational":[117],"autoencoder":[118],"tasked":[119],"with":[120,252],"learning":[121],"input":[125],"samples":[126,182],"embedding":[128],"it":[129,238],"along":[130],"one":[131,210,241],"dimension.":[133],"Aided":[134],"by":[135],"auxiliary":[137],"adversarial":[138],"loss":[139],"term":[140],"promoting":[141],"disentanglement,":[142],"effectively":[144],"regularizes":[145],"space,":[148],"thus":[149],"enabling":[150],"explicit":[151],"control":[152],"over":[153],"newly":[157],"generated":[158],"patterns.":[159],"Trained":[160],"large":[163],"corpus":[164],"MIDI":[166],"files":[167],"recordings,":[171],"method":[174],"proved":[175],"capable":[176],"generating":[178],"realistic":[181],"at":[183],"desired":[185],"value.":[187],"In":[188],"our":[189],"experiments,":[190],"output":[191],"target":[193],"complexities":[194],"show":[195],"high":[197],"correlation,":[198],"space":[202],"appears":[203],"interpretable":[204],"continuously":[206],"navigable.":[207],"On":[208,234],"hand,":[211,237],"can":[214],"readily":[215],"contribute":[216],"wide":[219],"range":[220],"creative":[222],"applications,":[223],"including,":[224],"instance,":[226],"assisted":[227],"composition":[229],"automatic":[231],"generation.":[233],"other":[236],"brings":[239],"us":[240],"step":[242],"closer":[243],"achieving":[245],"ambitious":[247],"goal":[248],"equipping":[250],"machines":[251],"human-like":[254],"features":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
