{"id":"https://openalex.org/W4224932515","doi":"https://doi.org/10.1109/icassp43922.2022.9747884","title":"Audio-To-Symbolic Arrangement Via Cross-Modal Music Representation Learning","display_name":"Audio-To-Symbolic Arrangement Via Cross-Modal Music Representation Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932515","doi":"https://doi.org/10.1109/icassp43922.2022.9747884"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747884","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100420916","display_name":"Ziyu Wang","orcid":"https://orcid.org/0000-0002-4697-5183"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I350617331","display_name":"Shanghai Conservatory of Music","ror":"https://ror.org/012f6xc93","country_code":"CN","type":"education","lineage":["https://openalex.org/I350617331"]},{"id":"https://openalex.org/I258800397","display_name":"New York University Shanghai","ror":"https://ror.org/02vpsdb40","country_code":"CN","type":"education","lineage":["https://openalex.org/I258800397","https://openalex.org/I57206974"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziyu Wang","raw_affiliation_strings":["NYU,Music X Lab,Shanghai","Music X Lab, NYU, Shanghai","ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"NYU,Music X Lab,Shanghai","institution_ids":["https://openalex.org/I350617331","https://openalex.org/I258800397"]},{"raw_affiliation_string":"Music X Lab, NYU, Shanghai","institution_ids":["https://openalex.org/I258800397"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068847379","display_name":"Dejing Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dejing Xu","raw_affiliation_strings":["Tencent PCG,ARC Lab","ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027959958","display_name":"Gus Xia","orcid":"https://orcid.org/0000-0003-3629-906X"},"institutions":[{"id":"https://openalex.org/I258800397","display_name":"New York University Shanghai","ror":"https://ror.org/02vpsdb40","country_code":"CN","type":"education","lineage":["https://openalex.org/I258800397","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I350617331","display_name":"Shanghai Conservatory of Music","ror":"https://ror.org/012f6xc93","country_code":"CN","type":"education","lineage":["https://openalex.org/I350617331"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gus Xia","raw_affiliation_strings":["NYU,Music X Lab,Shanghai","Music X Lab, NYU, Shanghai"],"affiliations":[{"raw_affiliation_string":"NYU,Music X Lab,Shanghai","institution_ids":["https://openalex.org/I350617331","https://openalex.org/I258800397"]},{"raw_affiliation_string":"Music X Lab, NYU, Shanghai","institution_ids":["https://openalex.org/I258800397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["Tencent PCG,ARC Lab","ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100420916"],"corresponding_institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I258800397","https://openalex.org/I350617331"],"apc_list":null,"apc_paid":null,"fwci":0.4909,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5671406,"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":"181","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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/melody","display_name":"Melody","score":0.7753932476043701},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7228951454162598},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.7020132541656494},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.5474593639373779},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5215924978256226},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.513340413570404},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4851894974708557},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.45180219411849976},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4404986500740051},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.436409056186676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39793339371681213},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.207086443901062},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14519277215003967},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09153226017951965},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0909816324710846}],"concepts":[{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.7753932476043701},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228951454162598},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.7020132541656494},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.5474593639373779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5215924978256226},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.513340413570404},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4851894974708557},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.45180219411849976},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4404986500740051},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.436409056186676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39793339371681213},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.207086443901062},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14519277215003967},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09153226017951965},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0909816324710846},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747884","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2105143211","https://openalex.org/W2398002958","https://openalex.org/W2771567333","https://openalex.org/W2797595207","https://openalex.org/W2805697608","https://openalex.org/W2899724567","https://openalex.org/W2903916098","https://openalex.org/W2906214917","https://openalex.org/W2948574791","https://openalex.org/W2950547518","https://openalex.org/W2964706117","https://openalex.org/W2990800437","https://openalex.org/W3000389243","https://openalex.org/W3037149862","https://openalex.org/W3047453285","https://openalex.org/W3049174246","https://openalex.org/W3049247973","https://openalex.org/W3049637270","https://openalex.org/W3152285961","https://openalex.org/W4293775315","https://openalex.org/W4394661832","https://openalex.org/W6631190155","https://openalex.org/W6712576946","https://openalex.org/W6745851314","https://openalex.org/W6746168993","https://openalex.org/W6751598888","https://openalex.org/W6755182157","https://openalex.org/W6763362620","https://openalex.org/W6770388877","https://openalex.org/W6771763809","https://openalex.org/W6781553146","https://openalex.org/W6781910838","https://openalex.org/W6782288222","https://openalex.org/W6782602824","https://openalex.org/W6793837709","https://openalex.org/W6799044462","https://openalex.org/W6950011876"],"related_works":["https://openalex.org/W2547055343","https://openalex.org/W2804082714","https://openalex.org/W2086473573","https://openalex.org/W1566263950","https://openalex.org/W2039049596","https://openalex.org/W1908769745","https://openalex.org/W3134670663","https://openalex.org/W4297791980","https://openalex.org/W2144131839","https://openalex.org/W2133554502"],"abstract_inverted_index":{"Could":[0],"we":[1,24,63],"automatically":[2],"derive":[3],"the":[4,12,20,37,50,54,77,103,114,116],"score":[5,110],"of":[6,14,45,105],"a":[7,15,65,88,96,123],"piano":[8,46],"accompaniment":[9],"based":[10],"on":[11],"audio":[13,38,55,86,129,141],"pop":[16],"song?":[17],"This":[18],"is":[19,120,130],"audio-to-symbolic":[21],"arrangement":[22,31],"problem":[23],"tackle":[25],"in":[26,146],"this":[27,61],"paper.":[28],"A":[29],"good":[30],"model":[32,138],"should":[33],"not":[34],"only":[35,128],"consider":[36],"content":[39],"but":[40],"also":[41],"have":[42],"prior":[43],"knowledge":[44],"composition":[47],"(so":[48],"that":[49,100,136],"generation":[51,147],"\"sounds":[52],"like\"":[53],"and":[56,73,79,87,127,143],"meanwhile":[57],"maintains":[58],"musicality).":[59],"To":[60],"end,":[62,115],"contribute":[64],"cross-modal":[66],"representation-learning":[67],"model,":[68],"which":[69],"1)":[70],"extracts":[71],"chord":[72],"melodic":[74],"information":[75,107,142],"from":[76,84,108],"audio,":[78],"2)":[80],"learns":[81],"texture":[82,106,118],"representation":[83],"both":[85],"corrupted":[89,109],"ground":[90],"truth":[91],"arrangement.":[92],"We":[93],"further":[94],"introduce":[95],"tailored":[97],"training":[98],"strategy":[99],"gradually":[101],"shifts":[102],"source":[104],"to":[111,122],"audio.":[112],"In":[113],"score-based":[117],"posterior":[119],"reduced":[121],"standard":[124],"normal":[125],"distribution,":[126],"needed":[131],"for":[132],"inference.":[133],"Experiments":[134],"show":[135],"our":[137],"captures":[139],"major":[140],"outperforms":[144],"baselines":[145],"quality.":[148],"<sup":[149],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}