{"id":"https://openalex.org/W4392903372","doi":"https://doi.org/10.1109/icassp48485.2024.10445979","title":"Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis","display_name":"Performance Conditioning for Diffusion-Based Multi-Instrument Music Synthesis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903372","doi":"https://doi.org/10.1109/icassp48485.2024.10445979"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5066394268","display_name":"Ben Maman","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Ben Maman","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032789917","display_name":"Johannes Zeitler","orcid":"https://orcid.org/0000-0003-2171-7679"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johannes Zeitler","raw_affiliation_strings":["International Audio Laboratories Erlangen,Germany","International Audio Laboratories Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard M\u00fcller","raw_affiliation_strings":["International Audio Laboratories Erlangen,Germany","International Audio Laboratories Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001922143","display_name":"Amit H. Bermano","orcid":"https://orcid.org/0000-0002-3592-1112"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Amit H. Bermano","raw_affiliation_strings":["Tel Aviv University"],"affiliations":[{"raw_affiliation_string":"Tel Aviv University","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066394268"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":1.0246,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7282217,"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":"5045","last_page":"5049"},"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":0.9995999932289124,"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":0.9966999888420105,"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/timbre","display_name":"Timbre","score":0.922553539276123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.79121994972229},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6196209788322449},{"id":"https://openalex.org/keywords/instrumentation","display_name":"Instrumentation (computer programming)","score":0.48388394713401794},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4788667857646942},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.47071072459220886},{"id":"https://openalex.org/keywords/sonification","display_name":"Sonification","score":0.4263792037963867},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41777315735816956},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4176235496997833},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40930747985839844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28259703516960144},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.1803629994392395},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08373907208442688}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.922553539276123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79121994972229},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6196209788322449},{"id":"https://openalex.org/C118530786","wikidata":"https://www.wikidata.org/wiki/Q1134732","display_name":"Instrumentation (computer programming)","level":2,"score":0.48388394713401794},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4788667857646942},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47071072459220886},{"id":"https://openalex.org/C91607612","wikidata":"https://www.wikidata.org/wiki/Q1416058","display_name":"Sonification","level":2,"score":0.4263792037963867},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41777315735816956},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4176235496997833},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40930747985839844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28259703516960144},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.1803629994392395},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08373907208442688},{"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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1997097421","display_name":null,"funder_award_id":"86/10","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G3526477989","display_name":null,"funder_award_id":"41629","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G5106512922","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5207180353","display_name":null,"funder_award_id":"686/10","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G7315415636","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G7568119934","display_name":null,"funder_award_id":"328416299","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320873","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2526050071","https://openalex.org/W2760103357","https://openalex.org/W2962721334","https://openalex.org/W2972478942","https://openalex.org/W3006926732","https://openalex.org/W3215615641","https://openalex.org/W4212774754","https://openalex.org/W4221145412","https://openalex.org/W4319989813","https://openalex.org/W4323076533","https://openalex.org/W4386065807","https://openalex.org/W6732646663","https://openalex.org/W6736723571","https://openalex.org/W6755182157","https://openalex.org/W6755961364","https://openalex.org/W6779823529","https://openalex.org/W6810708459","https://openalex.org/W6810809420","https://openalex.org/W6839133533","https://openalex.org/W6849635556","https://openalex.org/W6850082022"],"related_works":["https://openalex.org/W2037604299","https://openalex.org/W2107071826","https://openalex.org/W2007010327","https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531"],"abstract_inverted_index":{"Generating":[0],"multi-instrument":[1,48],"music":[2,5,75,92],"from":[3,101],"symbolic":[4],"representations":[6],"is":[7,26,106,134],"an":[8],"important":[9],"task":[10],"in":[11,23,32],"Music":[12],"Information":[13],"Retrieval":[14],"(MIR).":[15],"A":[16],"central":[17],"but":[18],"still":[19],"largely":[20],"unsolved":[21],"problem":[22],"this":[24,41],"context":[25],"musically":[27],"and":[28,59,69,95,114,124,132],"acoustically":[29],"informed":[30],"control":[31,46],"the":[33,37,87],"generation":[34],"process.":[35],"As":[36],"main":[38],"contribution":[39],"of":[40,47,67,97],"work,":[42],"we":[43,78],"propose":[44],"enhancing":[45],"synthesis":[49],"by":[50],"conditioning":[51,81],"a":[52,56,83],"generative":[53,76,88],"model":[54,89],"on":[55,72],"specific":[57,98,102],"performance":[58,80],"recording":[60],"environment,":[61],"thus":[62],"allowing":[63,121],"for":[64],"better":[65],"guidance":[66],"timbre":[68,96,123],"style.":[70],"Building":[71],"state-of-the-art":[73,116],"diffusion-based":[74],"models,":[77],"introduce":[79],"-":[82],"simple":[84],"tool":[85],"indicating":[86],"to":[90],"synthesize":[91],"with":[93,111],"style":[94,125],"instruments":[99],"taken":[100],"performances.":[103],"Our":[104,127],"prototype":[105],"evaluated":[107],"using":[108],"uncurated":[109],"performances":[110],"diverse":[112],"instrumentation":[113],"achieves":[115],"FAD":[117],"realism":[118],"scores":[119],"while":[120],"novel":[122],"control.":[126],"project":[128],"page,":[129],"including":[130],"samples":[131],"demonstrations,":[133],"available":[135],"at":[136],"benadar293.github.io/midipm.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
