{"id":"https://openalex.org/W4214485929","doi":"https://doi.org/10.1145/3508546.3508612","title":"ViT-based VQ-VAE Generative Network for Accompaniment Generation","display_name":"ViT-based VQ-VAE Generative Network for Accompaniment Generation","publication_year":2021,"publication_date":"2021-12-22","ids":{"openalex":"https://openalex.org/W4214485929","doi":"https://doi.org/10.1145/3508546.3508612"},"language":"en","primary_location":{"id":"doi:10.1145/3508546.3508612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508546.3508612","pdf_url":null,"source":{"id":"https://openalex.org/S4363608505","display_name":"2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","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/A5058104443","display_name":"Kai Song","orcid":"https://orcid.org/0000-0002-1851-3264"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Song","raw_affiliation_strings":["School of Software Engineering,, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering,, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042222287","display_name":"Xia Liang","orcid":"https://orcid.org/0000-0001-6252-2195"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia Liang","raw_affiliation_strings":["School of Software Engineering,, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering,, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112446278","display_name":"Junmin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junmin Wu","raw_affiliation_strings":["School of Software Engineering,, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering,, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.5439,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65889012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.993399977684021,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9793999791145325,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6900972723960876},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6721096038818359},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6018001437187195},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5224339365959167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4739147424697876},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46361950039863586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37824803590774536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900972723960876},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6721096038818359},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6018001437187195},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5224339365959167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4739147424697876},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46361950039863586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37824803590774536},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3508546.3508612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3508546.3508612","pdf_url":null,"source":{"id":"https://openalex.org/S4363608505","display_name":"2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W2559655401","https://openalex.org/W2612690371","https://openalex.org/W2618530766","https://openalex.org/W2752796333","https://openalex.org/W2772474126","https://openalex.org/W2798861951","https://openalex.org/W2919624000","https://openalex.org/W2963925437","https://openalex.org/W2992790584","https://openalex.org/W3047325651","https://openalex.org/W3092850823","https://openalex.org/W3154236293","https://openalex.org/W4212774754","https://openalex.org/W6633499030","https://openalex.org/W6735913928","https://openalex.org/W6762931180","https://openalex.org/W6781423933"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2163679795","https://openalex.org/W2736714427","https://openalex.org/W2137816434","https://openalex.org/W2017956276","https://openalex.org/W2048606991"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"accompaniment":[3,50,61,63,106,125],"generation":[4,51],"has":[5,65,82,126],"become":[6],"one":[7],"of":[8,60,80,97,103,109,116,119,141,144,148,175,181],"the":[9,32,58,83,87,95,101,137,160,163,172,179,186],"hottest":[10],"topics":[11],"in":[12,90,100,162],"deep":[13],"learning":[14],"and":[15,27,52,112,129,139,168,178],"many":[16,66],"researchers":[17],"work":[18],"on":[19],"it.":[20],"However,":[21],"most":[22],"prior":[23],"works":[24],"are":[25],"unstable":[26],"lack":[28],"harmony,":[29],"which":[30,92,122],"makes":[31],"results":[33,184],"they":[34],"generate":[35],"far":[36],"from":[37],"satisfying":[38],"to":[39,48,57,85],"human":[40],"ears.":[41],"To":[42],"address":[43],"this":[44,145],"problem,":[45],"we":[46,69,133],"propose":[47],"combine":[49],"music":[53,102],"theory.":[54],"Firstly,":[55],"according":[56],"characteristic":[59],"that":[62,124],"itself":[64],"fixed":[67],"patterns,":[68],"employ":[70],"VQ-VAE":[71,81,142],"as":[72,136,154,156],"our":[73,176,182],"generative":[74],"framework.":[75],"The":[76],"component":[77],"called":[78],"codebook":[79],"capability":[84,147],"learn":[86],"common":[88],"patterns":[89],"accompaniment,":[91],"coincides":[93],"with":[94],"idea":[96],"pattern":[98],"writing":[99],"accompaniment.":[104],"Moreover,":[105],"is":[107],"composed":[108],"multiple":[110],"tracks":[111,161],"every":[113],"track":[114],"consists":[115],"a":[117],"sequence":[118,152],"musical":[120],"notes,":[121],"means":[123],"both":[127],"temporal":[128],"spatial":[130],"information.":[131],"So,":[132],"introduce":[134],"ViT":[135],"encoder":[138],"decoder":[140],"because":[143],"model's":[146],"simultaneously":[149],"capturing":[150],"time":[151,165],"information":[153,158],"well":[155],"harmony":[157],"between":[159],"same":[164],"slice.":[166],"Objective":[167],"subjective":[169],"evaluations":[170],"demonstrate":[171],"above":[173],"features":[174],"work,":[177],"quality":[180],"generated":[183],"reach":[185],"state-of-the-art":[187],"level.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}