{"id":"https://openalex.org/W4406861241","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849230","title":"On the Importance of Time and Pitch Relativity for Transformer-Based Symbolic Music Generation","display_name":"On the Importance of Time and Pitch Relativity for Transformer-Based Symbolic Music Generation","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406861241","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849230"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5092867554","display_name":"Tatsuro Inaba","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuro Inaba","raw_affiliation_strings":["Kyoto University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Kyoto University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043140898","display_name":"Eita Nakamura","orcid":"https://orcid.org/0000-0003-4097-6027"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eita Nakamura","raw_affiliation_strings":["Kyushu University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu University,Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32753917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9976000189781189,"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":0.9976000189781189,"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/T11309","display_name":"Music and Audio Processing","score":0.9800000190734863,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9775999784469604,"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/transformer","display_name":"Transformer","score":0.6002263426780701},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.531281590461731},{"id":"https://openalex.org/keywords/theory-of-relativity","display_name":"Theory of relativity","score":0.4109901189804077},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.3003632724285126},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19997510313987732},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.19128739833831787},{"id":"https://openalex.org/keywords/theoretical-physics","display_name":"Theoretical physics","score":0.15761932730674744},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10922977328300476}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6002263426780701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.531281590461731},{"id":"https://openalex.org/C149324446","wikidata":"https://www.wikidata.org/wiki/Q43514","display_name":"Theory of relativity","level":2,"score":0.4109901189804077},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.3003632724285126},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19997510313987732},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.19128739833831787},{"id":"https://openalex.org/C33332235","wikidata":"https://www.wikidata.org/wiki/Q18362","display_name":"Theoretical physics","level":1,"score":0.15761932730674744},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10922977328300476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":19,"referenced_works":["https://openalex.org/W2788156829","https://openalex.org/W2963408210","https://openalex.org/W2963925437","https://openalex.org/W3092879656","https://openalex.org/W3173187964","https://openalex.org/W3175663427","https://openalex.org/W4372259826","https://openalex.org/W4377140494","https://openalex.org/W4377719641","https://openalex.org/W4382239517","https://openalex.org/W4385245566","https://openalex.org/W4392077356","https://openalex.org/W6629849291","https://openalex.org/W6676368125","https://openalex.org/W6755406732","https://openalex.org/W6781423933","https://openalex.org/W6781910838","https://openalex.org/W6803088475","https://openalex.org/W6846234567"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2864363823"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"experimental":[3],"investigation":[4],"of":[5,13,46,59,65,81,98,109,129],"music":[6,22,66,157],"representations":[7],"to":[8,69,77,113,156],"draw":[9],"the":[10,14,17,29,54,57,70,78,85,107,110,115,125,139,159,165,170],"full":[11],"potential":[12],"Transformer":[15,30,172],"with":[16,67,175],"self-attention":[18,111],"mechanism":[19,112],"for":[20,33,53,158],"symbolic":[21],"generation.":[23],"To":[24,142],"use":[25],"sequence-to-sequence":[26],"model":[27],"like":[28],"originally":[31],"proposed":[32,171],"natural":[34],"language":[35],"processing,":[36],"one":[37],"typically":[38],"serializes":[39],"a":[40,44,148],"musical":[41,82],"score":[42,179],"into":[43],"sequence":[45],"event-":[47,176],"or":[48,177],"note-based":[49,178],"tokens":[50],"without":[51],"concern":[52],"impact":[55],"on":[56],"quality":[58],"generated":[60],"music.":[61],"The":[62],"semantic":[63],"invariance":[64],"respect":[68],"time":[71,130,151],"and":[72,91,100,120,127,131,152],"pitch":[73,92,132,153],"shifts":[74],"is":[75,122],"attributed":[76],"positional":[79],"relativity":[80,126],"notes":[83],"over":[84],"time-pitch":[86],"plane":[87],"in":[88,138],"which":[89],"beats":[90],"classes":[93],"are":[94,134],"repeated":[95],"at":[96],"intervals":[97],"bars":[99],"octaves,":[101],"respectively.":[102],"We":[103],"here":[104],"hypothesize":[105],"that":[106,169],"capability":[108],"learn":[114],"musically":[116],"meaningful":[117],"rhythm,":[118],"melody,":[119],"harmony":[121],"limited":[123],"because":[124],"cyclicity":[128],"information":[133],"not":[135],"explicitly":[136],"represented":[137],"token":[140],"sequence.":[141],"solve":[143],"this":[144],"problem,":[145],"we":[146],"propose":[147],"cyclicity-aware":[149],"relative":[150],"encoding":[154],"unique":[155],"attention":[160],"mechanism.":[161],"Comprehensive":[162],"evaluation":[163],"using":[164],"POP909":[166],"dataset":[167],"demonstrated":[168],"works":[173],"better":[174],"tokenization1.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}