{"id":"https://openalex.org/W4388726501","doi":"https://doi.org/10.1109/gcce59613.2023.10315503","title":"Multi-Track Music Generation with WGAN-GP and Attention Mechanisms","display_name":"Multi-Track Music Generation with WGAN-GP and Attention Mechanisms","publication_year":2023,"publication_date":"2023-10-10","ids":{"openalex":"https://openalex.org/W4388726501","doi":"https://doi.org/10.1109/gcce59613.2023.10315503"},"language":"en","primary_location":{"id":"doi:10.1109/gcce59613.2023.10315503","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce59613.2023.10315503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 12th Global Conference on Consumer Electronics (GCCE)","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/A5065200178","display_name":"Luyu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Luyu Chen","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102580059","display_name":"Lin Shen","orcid":"https://orcid.org/0000-0002-9746-7023"},"institutions":[{"id":"https://openalex.org/I142415962","display_name":"Beijing Institute of Education","ror":"https://ror.org/03aefdx31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142415962"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Shen","raw_affiliation_strings":["Beijing Institute of Technology,School of Medical Technology,Beijing,China,100081","Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Medical Technology,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I142415962","https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102521674","display_name":"Dan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Yu","raw_affiliation_strings":["Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Computer Science and Technology,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356864","display_name":"Zhihua Wang","orcid":"https://orcid.org/0000-0001-6567-0759"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I3125079907","display_name":"Japan Graduate School of Education University","ror":"https://ror.org/03a6vay74","country_code":"JP","type":"education","lineage":["https://openalex.org/I3125079907"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhihua Wang","raw_affiliation_strings":["The University of Tokyo,Educational Physiology Laboratory, Graduate School of Education,Tokyo,Japan,113-0033"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Educational Physiology Laboratory, Graduate School of Education,Tokyo,Japan,113-0033","institution_ids":["https://openalex.org/I3125079907","https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072365199","display_name":"Kun Qian","orcid":"https://orcid.org/0000-0001-8255-2527"},"institutions":[{"id":"https://openalex.org/I142415962","display_name":"Beijing Institute of Education","ror":"https://ror.org/03aefdx31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142415962"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Qian","raw_affiliation_strings":["Beijing Institute of Technology,School of Medical Technology,Beijing,China,100081","Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Medical Technology,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I142415962","https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380066","display_name":"Bin Hu","orcid":"https://orcid.org/0000-0003-3514-5413"},"institutions":[{"id":"https://openalex.org/I142415962","display_name":"Beijing Institute of Education","ror":"https://ror.org/03aefdx31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142415962"]},{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Hu","raw_affiliation_strings":["Beijing Institute of Technology,School of Medical Technology,Beijing,China,100081","Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Medical Technology,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Key Laboratory of Brain Health Intelligent Evaluation and Intervention, Ministry of Education, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I142415962","https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Imperial College London,GLAM &#x2013; the Group on Language, Audio, &#x0026; Music,London,UK,SW7 2AZ"],"affiliations":[{"raw_affiliation_string":"Imperial College London,GLAM &#x2013; the Group on Language, Audio, &#x0026; Music,London,UK,SW7 2AZ","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087660235","display_name":"Yoshiharu Yamamoto","orcid":"https://orcid.org/0000-0002-1132-0355"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I3125079907","display_name":"Japan Graduate School of Education University","ror":"https://ror.org/03a6vay74","country_code":"JP","type":"education","lineage":["https://openalex.org/I3125079907"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiharu Yamamoto","raw_affiliation_strings":["The University of Tokyo,Educational Physiology Laboratory, Graduate School of Education,Tokyo,Japan,113-0033"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Educational Physiology Laboratory, Graduate School of Education,Tokyo,Japan,113-0033","institution_ids":["https://openalex.org/I3125079907","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5065200178"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16023033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"606","last_page":"607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9968000054359436,"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":0.9901999831199646,"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":0.7932493686676025},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5795618891716003},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.5643892288208008},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5076981782913208},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.4970691502094269},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4967935383319855},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4448520839214325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43784698843955994},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3474006652832031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34704965353012085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932493686676025},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5795618891716003},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.5643892288208008},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5076981782913208},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.4970691502094269},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4967935383319855},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4448520839214325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43784698843955994},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3474006652832031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34704965353012085},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce59613.2023.10315503","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce59613.2023.10315503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 12th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309618","display_name":"Ministry of Science and Technology","ror":"https://ror.org/02b207r52"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W2772474126","https://openalex.org/W3209794146","https://openalex.org/W4200610539","https://openalex.org/W4289752563","https://openalex.org/W4318696316","https://openalex.org/W6735913928","https://openalex.org/W6752378368"],"related_works":["https://openalex.org/W2072492413","https://openalex.org/W2997159972","https://openalex.org/W4296378967","https://openalex.org/W2064134577","https://openalex.org/W2373995729","https://openalex.org/W3203096336","https://openalex.org/W2157038729","https://openalex.org/W2393707162","https://openalex.org/W3005996785","https://openalex.org/W4386984417"],"abstract_inverted_index":{"Music":[0],"generation":[1,102],"with":[2,40,92],"artificial":[3],"intelligence":[4],"is":[5],"a":[6,34,54],"complex":[7],"and":[8,25,52,80,95,100],"captivating":[9],"task.":[10],"The":[11],"utilisation":[12],"of":[13],"generative":[14],"adversarial":[15],"networks":[16],"(GANs)":[17],"has":[18],"exhibited":[19],"promising":[20],"outcomes":[21],"in":[22,58,74],"producing":[23],"realistic":[24],"diverse":[26],"music":[27,46,70,91],"compositions.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,67],"propose":[33],"model":[35,49,87],"based":[36],"on":[37],"Wasserstein":[38],"GAN":[39],"gradient":[41],"penalty":[42],"(WGAN-GP)":[43],"for":[44],"multi-track":[45,90],"generation.":[47],"This":[48],"incorporates":[50],"self-attention":[51],"introduces":[53],"novel":[55],"cross-attention":[56],"mechanism":[57],"the":[59],"generator":[60],"to":[61,71,76],"enhance":[62],"its":[63],"expressive":[64],"capability.":[65],"Additionally,":[66],"transpose":[68],"all":[69],"C":[72],"major":[73],"training":[75],"ensure":[77],"data":[78],"consistency":[79],"quality.":[81,103],"Experimental":[82],"results":[83],"demonstrate":[84],"that":[85],"our":[86],"can":[88],"produce":[89],"enhanced":[93],"rhythm":[94],"sound":[96],"characteristics,":[97],"accelerate":[98],"convergence,":[99],"improve":[101]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
