{"id":"https://openalex.org/W4221167052","doi":"https://doi.org/10.1109/icassp43922.2022.9746978","title":"Upmixing Via Style Transfer: A Variational Autoencoder for Disentangling Spatial Images And Musical Content","display_name":"Upmixing Via Style Transfer: A Variational Autoencoder for Disentangling Spatial Images And Musical Content","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221167052","doi":"https://doi.org/10.1109/icassp43922.2022.9746978"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746978","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":"conference-paper","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/A5004403714","display_name":"Haici Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haici Yang","raw_affiliation_strings":["Indiana University,Dept. of Intelligent Systems Engineering,Bloomington,IN,USA","Dept. of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Dept. of Intelligent Systems Engineering,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Dept. of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072310429","display_name":"Sanna Wager","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanna Wager","raw_affiliation_strings":["Amazon Lab126,Cambridge,MA,USA","Amazon Lab126, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Lab126, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109522220","display_name":"Spencer Russell","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spencer Russell","raw_affiliation_strings":["Amazon Lab126,Cambridge,MA,USA","Amazon Lab126, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Lab126, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047810206","display_name":"Mike Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Luo","raw_affiliation_strings":["Amazon Lab126,Cambridge,MA,USA","Amazon Lab126, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Lab126, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Indiana University,Dept. of Intelligent Systems Engineering,Bloomington,IN,USA","Amazon Lab126, Cambridge, MA, USA","Dept. of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University,Dept. of Intelligent Systems Engineering,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Amazon Lab126, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Dept. of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059055507","display_name":"Wontak Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wontak Kim","raw_affiliation_strings":["Amazon Lab126,Cambridge,MA,USA","Amazon Lab126, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Lab126, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5537,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58588915,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"426","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9904999732971191,"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":0.9904999732971191,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9900000095367432,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9897000193595886,"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/autoencoder","display_name":"Autoencoder","score":0.8554465770721436},{"id":"https://openalex.org/keywords/panning","display_name":"Panning (audio)","score":0.8164862394332886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.687548041343689},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6423494219779968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6243639588356018},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.6132252216339111},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5362880229949951},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48826003074645996},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.420657217502594},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41575708985328674},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4122757017612457},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4061563313007355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20236435532569885},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16091805696487427}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8554465770721436},{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.8164862394332886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.687548041343689},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6423494219779968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243639588356018},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.6132252216339111},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5362880229949951},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48826003074645996},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.420657217502594},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41575708985328674},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4122757017612457},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4061563313007355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20236435532569885},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16091805696487427},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746978","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":[{"id":"https://metadata.un.org/sdg/10","score":0.6399999856948853,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1501566231","https://openalex.org/W1505210257","https://openalex.org/W1522301498","https://openalex.org/W1549940068","https://openalex.org/W1556581483","https://openalex.org/W1563107828","https://openalex.org/W1959608418","https://openalex.org/W2002201796","https://openalex.org/W2115875660","https://openalex.org/W2127025863","https://openalex.org/W2274791487","https://openalex.org/W2560092415","https://openalex.org/W2802831984","https://openalex.org/W2963446712","https://openalex.org/W2963452667","https://openalex.org/W3001377302","https://openalex.org/W3119422267","https://openalex.org/W6630089114","https://openalex.org/W6630128341","https://openalex.org/W6631190155","https://openalex.org/W6632679385","https://openalex.org/W6633437517","https://openalex.org/W6633642426","https://openalex.org/W6640963894","https://openalex.org/W6678752530","https://openalex.org/W6751512325","https://openalex.org/W6773772901","https://openalex.org/W6894165537","https://openalex.org/W7062430579"],"related_works":["https://openalex.org/W2988134182","https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W2470043383","https://openalex.org/W4380551139","https://openalex.org/W2953501176","https://openalex.org/W2965095304","https://openalex.org/W2280377497","https://openalex.org/W3034474024","https://openalex.org/W4387506531"],"abstract_inverted_index":{"In":[0,26],"the":[1,9,15,18,22,43,53,60,67,74,79,90,103],"stereo-to-multichannel":[2],"upmixing":[3,86],"problem":[4],"for":[5],"music,":[6],"one":[7,94],"of":[8,17,81],"main":[10],"tasks":[11],"is":[12],"to":[13,41,51,66,77,96,113],"set":[14],"directionality":[16],"instrument":[19],"sources":[20],"in":[21,46],"multichannel":[23,47],"rendering":[24],"results.":[25],"this":[27],"paper,":[28],"we":[29,72],"propose":[30,84],"a":[31,38],"modified":[32],"variational":[33],"autoencoder":[34],"model":[35,118],"that":[36,116],"learns":[37],"latent":[39,62,75],"space":[40],"describe":[42],"spatial":[44,54,91,120],"images":[45,55,92,121],"music.":[48,68],"We":[49,83,106],"seek":[50],"disentangle":[52],"and":[56,98,109,126],"music":[57,124],"content,":[58],"so":[59],"learned":[61],"variables":[63,76],"are":[64],"invariant":[65],"At":[69],"test":[70],"time,":[71],"use":[73,87],"control":[78],"panning":[80,100],"sources.":[82],"two":[85],"cases:":[88],"transferring":[89],"from":[93,123],"song":[95],"another":[97],"blind":[99],"based":[101],"on":[102],"generative":[104],"model.":[105],"report":[107],"objective":[108],"subjective":[110],"evaluation":[111],"results":[112],"empirically":[114],"show":[115],"our":[117],"captures":[119],"separately":[122],"content":[125],"achieves":[127],"transfer-based":[128],"interactive":[129],"panning.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}