{"id":"https://openalex.org/W4221145412","doi":"https://doi.org/10.1109/icassp43922.2022.9747217","title":"Deep Performer: Score-to-Audio Music Performance Synthesis","display_name":"Deep Performer: Score-to-Audio Music Performance Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221145412","doi":"https://doi.org/10.1109/icassp43922.2022.9747217"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747217","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/A5073500422","display_name":"H.K. Dong","orcid":"https://orcid.org/0000-0002-5765-7594"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]},{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["NL","US"],"is_corresponding":true,"raw_author_name":"Hao-Wen Dong","raw_affiliation_strings":["Dolby Laboratories","University of California San Diego"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]},{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102733043","display_name":"Cong Zhou","orcid":"https://orcid.org/0000-0002-4379-0298"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cong Zhou","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021827617","display_name":"Julian McAuley","orcid":"https://orcid.org/0000-0003-0955-7588"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073500422"],"corresponding_institution_ids":["https://openalex.org/I116121188","https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":2.0892,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89352291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"951","last_page":"955"},"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":0.9991999864578247,"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":0.9918000102043152,"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":0.7589104175567627},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7480179071426392},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.672023594379425},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6633567810058594},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5918738842010498},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5347081422805786},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4749479591846466},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.4475925862789154},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.42781245708465576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3307586908340454},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.22183728218078613},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11927863955497742},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08716204762458801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589104175567627},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7480179071426392},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.672023594379425},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6633567810058594},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5918738842010498},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5347081422805786},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4749479591846466},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.4475925862789154},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.42781245708465576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3307586908340454},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.22183728218078613},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11927863955497742},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08716204762458801},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747217","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2606176153","https://openalex.org/W2783717582","https://openalex.org/W2784442816","https://openalex.org/W2890043615","https://openalex.org/W2899724567","https://openalex.org/W2910577860","https://openalex.org/W2946200149","https://openalex.org/W2950547518","https://openalex.org/W2951928450","https://openalex.org/W2962721334","https://openalex.org/W2963073614","https://openalex.org/W2963300588","https://openalex.org/W2963408210","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2965526162","https://openalex.org/W2970006822","https://openalex.org/W2971753973","https://openalex.org/W3000389243","https://openalex.org/W3047386385","https://openalex.org/W3081279708","https://openalex.org/W3161704465","https://openalex.org/W3174758275","https://openalex.org/W3196308991","https://openalex.org/W4225716783","https://openalex.org/W4297772864","https://openalex.org/W4362724041","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6736723571","https://openalex.org/W6739901393","https://openalex.org/W6747723547","https://openalex.org/W6748441789","https://openalex.org/W6754333143","https://openalex.org/W6755182157","https://openalex.org/W6758675244","https://openalex.org/W6763832098","https://openalex.org/W6766640929","https://openalex.org/W6767111847","https://openalex.org/W6767453231","https://openalex.org/W6771763809","https://openalex.org/W6781423933","https://openalex.org/W6796730497","https://openalex.org/W6798451072","https://openalex.org/W6810708459"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2380085135","https://openalex.org/W2558300772","https://openalex.org/W2385208723","https://openalex.org/W2355890546","https://openalex.org/W2040048036","https://openalex.org/W2607529793","https://openalex.org/W2978163245","https://openalex.org/W3033263360","https://openalex.org/W2072526973"],"abstract_inverted_index":{"Music":[0],"performance":[1,33],"synthesis":[2,22],"aims":[3],"to":[4],"synthesize":[5,94],"a":[6,10,56,60,71,103,114],"musical":[7],"score":[8],"into":[9],"natural":[11],"performance.":[12],"In":[13,102],"this":[14],"paper,":[15],"we":[16,45,69,106],"borrow":[17],"recent":[18],"advances":[19],"in":[20,59,119,141],"text-to-speech":[21],"and":[23,41,54,79,99,125],"present":[24,70],"the":[25,111,134],"Deep":[26],"Performer\u2014a":[27],"novel":[28],"system":[29],"for":[30,50],"score-to-audio":[31],"music":[32,37,95],"synthesis.":[34],"Unlike":[35],"speech,":[36],"often":[38],"contains":[39],"polyphony":[40,98],"long":[42],"notes.":[43],"Hence,":[44],"propose":[46],"two":[47],"new":[48,72],"techniques":[49],"handling":[51],"polyphonic":[52],"inputs":[53],"providing":[55],"fine-grained":[57],"conditioning":[58],"transformer":[61],"encoder-decoder":[62],"model.":[63],"To":[64],"train":[65],"our":[66,90,129],"proposed":[67,91,130],"system,":[68],"violin":[73],"dataset":[74,140],"consisting":[75],"of":[76,121],"paired":[77],"recordings":[78],"scores":[80],"along":[81],"with":[82,96],"estimated":[83],"alignments":[84],"between":[85],"them.":[86],"We":[87],"show":[88],"that":[89],"model":[92,131],"can":[93],"clear":[97],"harmonic":[100],"structures.":[101],"listening":[104],"test,":[105],"achieve":[107],"competitive":[108],"quality":[109],"against":[110],"baseline":[112,135],"model,":[113,118],"conditional":[115],"generative":[116],"audio":[117],"terms":[120],"pitch":[122],"accuracy,":[123],"timbre":[124],"noise":[126],"level.":[127],"Moreover,":[128],"significantly":[132],"outperforms":[133],"on":[136],"an":[137],"existing":[138],"piano":[139],"overall":[142],"quality.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
