{"id":"https://openalex.org/W4385764331","doi":"https://doi.org/10.24963/ijcai.2023/430","title":"Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem","display_name":"Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764331","doi":"https://doi.org/10.24963/ijcai.2023/430"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/430","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/430","pdf_url":"https://www.ijcai.org/proceedings/2023/0430.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0430.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068823292","display_name":"Emmanouil Karystinaios","orcid":"https://orcid.org/0000-0001-9354-8953"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Emmanouil Karystinaios","raw_affiliation_strings":["Johannes Kepler University Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Kepler University Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064606318","display_name":"Francesco Foscarin","orcid":"https://orcid.org/0000-0003-4634-7475"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Francesco Foscarin","raw_affiliation_strings":["Johannes Kepler University Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Kepler University Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Johannes Kepler University Linz, Austria","LIT AI Lab, Linz Institute of Technology, Austria","Johannes Kepler University Linz, Austria; LIT AI Lab, Linz Institute of Technology, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Kepler University Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT AI Lab, Linz Institute of Technology, Austria","institution_ids":[]},{"raw_affiliation_string":"Johannes Kepler University Linz, Austria; LIT AI Lab, Linz Institute of Technology, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068823292"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":0.5617,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63644813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3866","last_page":"3874"},"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":0.9980000257492065,"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":0.9958999752998352,"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":0.7627549171447754},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5658355951309204},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5109092593193054},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5052252411842346},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.43310272693634033},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4228728115558624},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41387686133384705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36802011728286743},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.3255234956741333},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2665121555328369}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627549171447754},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5658355951309204},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5109092593193054},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5052252411842346},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.43310272693634033},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4228728115558624},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41387686133384705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36802011728286743},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3255234956741333},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2665121555328369},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/430","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/430","pdf_url":"https://www.ijcai.org/proceedings/2023/0430.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/430","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/430","pdf_url":"https://www.ijcai.org/proceedings/2023/0430.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764331.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W28850873","https://openalex.org/W60026746","https://openalex.org/W203278212","https://openalex.org/W1500684166","https://openalex.org/W1592570595","https://openalex.org/W1989628686","https://openalex.org/W2021566302","https://openalex.org/W2115057260","https://openalex.org/W2121693708","https://openalex.org/W2132715541","https://openalex.org/W2140869193","https://openalex.org/W2162108390","https://openalex.org/W2169963314","https://openalex.org/W2171033594","https://openalex.org/W2340199271","https://openalex.org/W2343318362","https://openalex.org/W2557169239","https://openalex.org/W2578550227","https://openalex.org/W2604314403","https://openalex.org/W2804057010","https://openalex.org/W2906351695","https://openalex.org/W2946488335","https://openalex.org/W3035442500","https://openalex.org/W3149485574","https://openalex.org/W3193490249","https://openalex.org/W4281647609","https://openalex.org/W4281648547","https://openalex.org/W4287829537","https://openalex.org/W4293651439","https://openalex.org/W4294319184","https://openalex.org/W4297689203","https://openalex.org/W4308860664","https://openalex.org/W4399772608"],"related_works":["https://openalex.org/W2118466154","https://openalex.org/W2411659965","https://openalex.org/W2118371117","https://openalex.org/W2387677326","https://openalex.org/W2464878701","https://openalex.org/W4247380401","https://openalex.org/W2031608562","https://openalex.org/W2070348439","https://openalex.org/W2727800297","https://openalex.org/W2797744129"],"abstract_inverted_index":{"This":[0,85],"paper":[1],"targets":[2],"the":[3,8,67,82,120,124,190],"perceptual":[4],"task":[5,33,193],"of":[6,87,127,171,197],"separating":[7],"different":[9,198],"interacting":[10],"voices,":[11,172],"i.e.,":[12,43],"monophonic":[13,140],"melodic":[14,68],"streams,":[15],"in":[16,45,81,150],"a":[17,35,46,52,55,72,99,114,168],"polyphonic":[18],"musical":[19,56],"piece.":[20],"We":[21,184],"target":[22],"symbolic":[23],"music,":[24],"where":[25],"notes":[26,44,76],"are":[27,79,206],"explicitly":[28],"encoded,":[29],"and":[30,65,108,132,167,173,182,203],"model":[31],"this":[32,143],"as":[34,179],"Multi-Trajectory":[36],"Tracking":[37],"(MTT)":[38],"problem":[39],"from":[40,54],"discrete":[41],"observations,":[42],"pitch-time":[47],"space.":[48],"Our":[49,155],"approach":[50,156],"builds":[51],"graph":[53,101],"piece,":[57],"by":[58,70,94,98],"creating":[59],"one":[60,130,133],"node":[61,95],"for":[62,136,189],"every":[63,137],"note,":[64],"separates":[66],"trajectories":[69],"predicting":[71],"link":[73,135],"between":[74],"two":[75],"if":[77],"they":[78],"consecutive":[80],"same":[83],"voice/stream.":[84],"kind":[86],"local,":[88],"greedy":[89],"prediction":[90],"is":[91,162],"made":[92],"possible":[93],"embeddings":[96],"created":[97],"heterogeneous":[100],"neural":[102],"network":[103],"that":[104,118],"can":[105,174],"capture":[106],"inter-":[107],"intra-trajectory":[109],"information.":[110],"Furthermore,":[111],"we":[112],"propose":[113],"new":[115,186],"regularization":[116],"loss":[117,144],"encourages":[119],"output":[121],"to":[122,164],"respect":[123],"MTT":[125,153],"premise":[126],"at":[128],"most":[129],"incoming":[131],"outgoing":[134],"node,":[138],"favoring":[139],"(voice)":[141],"trajectories;":[142],"function":[145],"might":[146],"also":[147],"be":[148],"useful":[149],"other":[151],"general":[152],"scenarios.":[154],"does":[157],"not":[158],"use":[159],"domain-specific":[160],"heuristics,":[161],"scalable":[163],"longer":[165],"sequences":[166],"higher":[169],"number":[170],"handle":[175],"complex":[176],"cases":[177],"such":[178],"voice":[180,191],"inversions":[181],"overlaps.":[183],"reach":[185],"state-of-the-art":[187],"results":[188],"separation":[192],"on":[194,208],"classical":[195],"music":[196],"styles.":[199],"All":[200],"code,":[201],"data,":[202],"pretrained":[204],"models":[205],"available":[207],"https://github.com/manoskary/vocsep_ijcai2023":[209]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}