{"id":"https://openalex.org/W4304091524","doi":"https://doi.org/10.1145/3503161.3548368","title":"SongDriver: Real-time Music Accompaniment Generation without Logical Latency nor Exposure Bias","display_name":"SongDriver: Real-time Music Accompaniment Generation without Logical Latency nor Exposure Bias","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304091524","doi":"https://doi.org/10.1145/3503161.3548368"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548368","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5100413090","display_name":"Zihao Wang","orcid":"https://orcid.org/0000-0002-5613-3262"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihao Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577175","display_name":"Kejun Zhang","orcid":"https://orcid.org/0000-0002-0778-2303"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejun Zhang","raw_affiliation_strings":["Zhejiang University; Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China","Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University; Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100615784","display_name":"Yuxing Wang","orcid":"https://orcid.org/0009-0001-6874-8926"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxing Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374104","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0002-2647-3266"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061702317","display_name":"Qihao Liang","orcid":"https://orcid.org/0000-0002-3866-6081"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihao Liang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100542949","display_name":"Pengfei Yu","orcid":"https://orcid.org/0000-0002-2774-1058"},"institutions":[{"id":"https://openalex.org/I4210116247","display_name":"Jingchu University of Technology","ror":"https://ror.org/037kvhq82","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210116247"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Yu","raw_affiliation_strings":["Jingchu University of Technology, Jingmen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jingchu University of Technology, Jingmen, China","institution_ids":["https://openalex.org/I4210116247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111973410","display_name":"Yongsheng Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongsheng Feng","raw_affiliation_strings":["Shandong University, Weihai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University, Weihai, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330679","display_name":"Wenbo Liu","orcid":"https://orcid.org/0000-0002-2270-9606"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747434","display_name":"Yikai Wang","orcid":"https://orcid.org/0000-0001-8212-0222"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yikai Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102823228","display_name":"Yuntao Bao","orcid":"https://orcid.org/0009-0009-0568-4708"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuntao Bao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050090766","display_name":"Yiheng Yang","orcid":"https://orcid.org/0000-0003-3169-6162"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiheng Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5100413090"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.0906,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79855209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1057","last_page":"1067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9556999802589417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7906554937362671},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.744931161403656},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6357221603393555},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5477149486541748},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48457205295562744},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44063496589660645},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34279733896255493},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.31829309463500977},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.15405642986297607},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11561116576194763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906554937362671},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.744931161403656},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6357221603393555},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5477149486541748},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48457205295562744},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44063496589660645},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34279733896255493},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.31829309463500977},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.15405642986297607},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11561116576194763},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548368","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548368","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1537357046","https://openalex.org/W1975929202","https://openalex.org/W1981802837","https://openalex.org/W2030466815","https://openalex.org/W2142996485","https://openalex.org/W2593463961","https://openalex.org/W2772474126","https://openalex.org/W2898827701","https://openalex.org/W2939080131","https://openalex.org/W2940894295","https://openalex.org/W2963521413","https://openalex.org/W2997586082","https://openalex.org/W3034586846","https://openalex.org/W3092850823","https://openalex.org/W3124507227"],"related_works":["https://openalex.org/W2118466154","https://openalex.org/W2118371117","https://openalex.org/W2464878701","https://openalex.org/W4247380401","https://openalex.org/W3013946943","https://openalex.org/W3112683371","https://openalex.org/W3113198510","https://openalex.org/W1918576746","https://openalex.org/W3176125119","https://openalex.org/W4383650950"],"abstract_inverted_index":{"Real-time":[0],"music":[1,12,16,24,49,198,228],"accompaniment":[2,25,50,63,127],"generation":[3,26,51,64],"has":[4],"a":[5,33,47,74,103,141,196],"wide":[6],"range":[7],"of":[8,94,180],"applications":[9],"in":[10,83],"the":[11,87,90,111,126,129,146,150,160,165,178,201,209,249],"industry,":[13],"such":[14],"as":[15,205],"education":[17],"and":[18,30,38,85,218,243],"live":[19],"performances.":[20],"However,":[21],"automatic":[22],"real-time":[23,48,172],"is":[27,168,177],"still":[28],"understudied":[29],"often":[31,169],"faces":[32],"trade-off":[34],"between":[35],"logical":[36,54,134],"latency":[37,55],"exposure":[39,57,161],"bias.":[40,58],"In":[41,208],"this":[42,120,188],"paper,":[43],"we":[44,190,211],"propose":[45],"SongDriver,":[46],"system":[52],"without":[53],"nor":[56],"Specifically,":[59],"SongDriver":[60,123,143,213,234],"divides":[61],"one":[62],"task":[65],"into":[66],"two":[67],"phases:":[68],"1)":[69],"The":[70,99,230],"arrangement":[71],"phase,":[72,101],"where":[73,102],"Transformer":[75],"model":[76,105],"first":[77,151],"arranges":[78],"chords":[79,88,139,148],"for":[80,89,110,128,140,187],"input":[81,166],"melodies":[82,113],"real-time,":[84],"caches":[86],"next":[91],"phase":[92,152],"instead":[93],"playing":[95],"them":[96],"out.":[97],"2)":[98],"prediction":[100],"CRF":[104],"generates":[106,125],"playable":[107],"multi-track":[108],"accompaniments":[109],"coming":[112],"based":[114],"on":[115,214,240],"previously":[116],"cached":[117,147],"chords.":[118],"With":[119],"two-phase":[121],"strategy,":[122],"directly":[124],"upcoming":[130],"melody,":[131],"achieving":[132],"zero":[133],"latency.":[135,251],"Furthermore,":[136],"when":[137],"predicting":[138],"timestep,":[142],"refers":[144],"to":[145],"from":[149,195,224],"rather":[153],"than":[154],"its":[155],"previous":[156],"predictions,":[157],"which":[158],"avoids":[159],"bias":[162],"problem.":[163],"Since":[164],"length":[167],"constrained":[170],"under":[171],"conditions,":[173],"another":[174],"potential":[175],"problem":[176],"loss":[179],"long-term":[181,197],"sequential":[182],"information.":[183,207],"To":[184],"make":[185],"up":[186],"disadvantage,":[189],"extract":[191],"four":[192],"musical":[193],"features":[194],"piece":[199],"before":[200],"current":[202],"time":[203],"step":[204],"global":[206],"experiment,":[210],"train":[212],"some":[215],"open-source":[216],"datasets":[217],"an":[219],"original":[220],"\u00e0iMusic":[221],"Dataset":[222],"built":[223],"Chinese-style":[225],"modern":[226],"pop":[227],"sheets.":[229],"results":[231],"show":[232],"that":[233],"outperforms":[235],"existing":[236],"SOTA":[237],"(state-of-the-art)":[238],"models":[239],"both":[241],"objective":[242],"subjective":[244],"metrics,":[245],"meanwhile":[246],"significantly":[247],"reducing":[248],"physical":[250]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
