{"id":"https://openalex.org/W4361983259","doi":"https://doi.org/10.1109/taslp.2023.3263797","title":"The Power of Fragmentation: A Hierarchical Transformer Model for Structural Segmentation in Symbolic Music Generation","display_name":"The Power of Fragmentation: A Hierarchical Transformer Model for Structural Segmentation in Symbolic Music Generation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4361983259","doi":"https://doi.org/10.1109/taslp.2023.3263797"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3263797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3263797","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5029356396","display_name":"Guowei Wu","orcid":"https://orcid.org/0000-0002-3929-3598"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guowei Wu","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China","Guowei Wu, Shipei Liu, and Xiaoya Fan are with the School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-3929-3598","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Guowei Wu, Shipei Liu, and Xiaoya Fan are with the School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019633696","display_name":"Shipei Liu","orcid":"https://orcid.org/0000-0002-2801-7512"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shipei Liu","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China","Guowei Wu, Shipei Liu, and Xiaoya Fan are with the School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-2801-7512","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Guowei Wu, Shipei Liu, and Xiaoya Fan are with the School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055305202","display_name":"Xiaoya Fan","orcid":"https://orcid.org/0000-0002-5002-6968"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoya Fan","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, China","Guowei Wu, Shipei Liu, and Xiaoya Fan are with the School of Software, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-5002-6968","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"Guowei Wu, Shipei Liu, and Xiaoya Fan are with the School of Software, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":2.4356,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89746062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1409","last_page":"1420"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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":0.9943000078201294,"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":0.7537386417388916},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6082555055618286},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.6047304272651672},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.46235474944114685},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.44500166177749634},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43935853242874146},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.43193188309669495},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.42416995763778687},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4191078245639801},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39740434288978577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38606566190719604},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.13960692286491394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537386417388916},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6082555055618286},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.6047304272651672},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.46235474944114685},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.44500166177749634},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43935853242874146},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.43193188309669495},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.42416995763778687},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4191078245639801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39740434288978577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38606566190719604},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.13960692286491394},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3263797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3263797","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W637807415","https://openalex.org/W2058373514","https://openalex.org/W2603777577","https://openalex.org/W2772474126","https://openalex.org/W2898827701","https://openalex.org/W2939753704","https://openalex.org/W2949780888","https://openalex.org/W2964110616","https://openalex.org/W2982753834","https://openalex.org/W2997359842","https://openalex.org/W3017343282","https://openalex.org/W3030056709","https://openalex.org/W3040218036","https://openalex.org/W3094333478","https://openalex.org/W3097777922","https://openalex.org/W3102692503","https://openalex.org/W3108047681","https://openalex.org/W3108240585","https://openalex.org/W3114618842","https://openalex.org/W3211570179","https://openalex.org/W4285169270","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W4392530595","https://openalex.org/W6606948184","https://openalex.org/W6678448728","https://openalex.org/W6714004745","https://openalex.org/W6730558285","https://openalex.org/W6749351710","https://openalex.org/W6753579488","https://openalex.org/W6755182157","https://openalex.org/W6760601182","https://openalex.org/W6761628794","https://openalex.org/W6762796984","https://openalex.org/W6764679822","https://openalex.org/W6781678156","https://openalex.org/W6788864986","https://openalex.org/W6801284891","https://openalex.org/W6849550793","https://openalex.org/W6862732850"],"related_works":["https://openalex.org/W2753058862","https://openalex.org/W2547055343","https://openalex.org/W2163240950","https://openalex.org/W2804082714","https://openalex.org/W2086473573","https://openalex.org/W1566263950","https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W1908769745","https://openalex.org/W2039049596"],"abstract_inverted_index":{"Symbolic":[0],"music":[1,78,130,138,184,212],"generation":[2],"relies":[3],"on":[4,148],"the":[5,10,14,19,29,64,77,99,123,141,177],"contextual":[6,23],"representation":[7],"capabilities":[8],"of":[9,45,166,173,176,201],"generative":[11],"model,":[12],"where":[13],"most":[15],"prevalent":[16],"approach":[17],"is":[18,146],"Transformer-based":[20],"model.":[21],"Learning":[22],"representations":[24],"are":[25,208],"also":[26,127,190],"related":[27],"to":[28,57,75,91,112,121,134],"structural":[30],"elements":[31],"in":[32,61,115,162,194],"music,":[33],"i.e.,":[34],"intro,":[35],"verse,":[36],"and":[37,82,95,117,169,182,204],"chorus,":[38],"which":[39,207],"have":[40],"not":[41],"received":[42],"much":[43],"attention":[44,89],"scientific":[46],"publications.":[47],"In":[48,63,98],"this":[49],"paper,":[50],"we":[51,67,85,102],"propose":[52,103],"a":[53,70,87,104,118,129,136],"hierarchical":[54,105],"Transformer":[55,106],"model":[56,107,145,157],"learn":[58,92],"multiscale":[59,88],"contexts":[60],"music.":[62,125],"encoding":[65],"phase,":[66,101],"first":[68],"design":[69],"fragment":[71],"scope":[72],"localization":[73],"module":[74],"separate":[76],"parts":[79],"into":[80],"chords":[81],"sections.":[83,143],"Then,":[84],"use":[86],"mechanism":[90],"note-,":[93],"chord-,":[94],"section-level":[96],"contexts.":[97],"decoding":[100],"that":[108,155],"uses":[109],"fine":[110],"decoders":[111],"generate":[113],"sections":[114],"parallel":[116],"coarse":[119],"decoder":[120],"decode":[122],"combined":[124],"We":[126],"designed":[128],"style":[131,139],"normalization":[132],"layer":[133],"achieve":[135],"consistent":[137],"between":[140],"generated":[142],"Our":[144],"evaluated":[147],"two":[149],"open":[150],"MIDI":[151],"datasets.":[152],"Experiments":[153],"show":[154],"our":[156],"outperforms":[158],"other":[159],"comparative":[160],"models":[161],"50%":[163],"(6":[164],"out":[165,172],"12":[167,174],"metrics)":[168,175],"83.3%":[170],"(10":[171],"quantitative":[178],"metrics":[179],"for":[180],"short-":[181],"long-term":[183],"generation,":[185],"respectively.":[186],"Preliminary":[187],"visual":[188],"analysis":[189],"suggests":[191],"its":[192],"potential":[193],"following":[195],"compositional":[196],"rules,":[197],"such":[198],"as":[199],"reuse":[200],"rhythmic":[202],"patterns":[203],"critical":[205],"melodies,":[206],"associated":[209],"with":[210],"improved":[211],"quality.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}