{"id":"https://openalex.org/W4401610429","doi":"https://doi.org/10.1109/icasspw62465.2024.10626303","title":"Sound Source Separation Using Latent Variational Block-Wise Disentanglement","display_name":"Sound Source Separation Using Latent Variational Block-Wise Disentanglement","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401610429","doi":"https://doi.org/10.1109/icasspw62465.2024.10626303"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626303","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5014282181","display_name":"Karim Helwani","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":"Karim Helwani","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021883714","display_name":"Masahito Togami","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":"Masahito Togami","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","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":"Paris Smaragdis","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082904207","display_name":"Michael M. Goodwin","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":"Michael M. Goodwin","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.8343,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70363934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"750","last_page":"754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9470000267028809,"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/block","display_name":"Block (permutation group theory)","score":0.6739029884338379},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6331996321678162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5716444849967957},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5621678233146667},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36815589666366577},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34155014157295227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2978437840938568},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.11807674169540405},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09101760387420654}],"concepts":[{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6739029884338379},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6331996321678162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5716444849967957},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5621678233146667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36815589666366577},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34155014157295227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2978437840938568},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.11807674169540405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09101760387420654}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626303","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1505878979","https://openalex.org/W1546155242","https://openalex.org/W2105617050","https://openalex.org/W2109987668","https://openalex.org/W2113990625","https://openalex.org/W2155606012","https://openalex.org/W2162531249","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2766672686","https://openalex.org/W2883322837","https://openalex.org/W2905196628","https://openalex.org/W2943237054","https://openalex.org/W2950662112","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2970479424","https://openalex.org/W2972516210","https://openalex.org/W3004970274","https://openalex.org/W3010874390","https://openalex.org/W3015199127","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3099330747","https://openalex.org/W3140410199","https://openalex.org/W3163652268","https://openalex.org/W3198425604","https://openalex.org/W4212774754","https://openalex.org/W4224938485","https://openalex.org/W4295112158","https://openalex.org/W4404783458","https://openalex.org/W6677085345","https://openalex.org/W6745687250","https://openalex.org/W6756663807","https://openalex.org/W6763279430","https://openalex.org/W6803601570","https://openalex.org/W6840441895"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2073681303","https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W2287611352","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W2053286651","https://openalex.org/W4385464961","https://openalex.org/W2077498359"],"abstract_inverted_index":{"While":[0],"neural":[1,30,47],"network":[2,48],"approaches":[3,21,64],"have":[4],"made":[5],"significant":[6],"strides":[7],"in":[8,86,95],"resolving":[9],"classical":[10,43,63,130],"signal":[11,27,45,131],"processing":[12,28,132],"problems,":[13],"it":[14],"is":[15,99],"often":[16],"the":[17,56,73,96,109,115,119,123,129,145,150,165,175,178],"case":[18],"that":[19,22,71,114],"hybrid":[20,42],"draw":[23],"insight":[24],"from":[25],"both":[26],"and":[29,62,118,142,163],"networks":[31],"produce":[32],"more":[33],"complete":[34],"solutions.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,154],"present":[40],"a":[41,69,87,103,157,168],"digital":[44],"processing/deep":[46],"(DSP/DNN)":[49],"approach":[50],"to":[51,65,79,136,138,171],"source":[52],"separation":[53,93],"(SS)":[54],"highlighting":[55],"theoretical":[57,133],"link":[58],"between":[59],"variational":[60,104,120],"autoencoder":[61],"SS.":[66],"We":[67,111],"propose":[68],"system":[70],"transforms":[72],"single":[74],"channel":[75],"under-determined":[76],"SS":[77,84],"task":[78,94,124],"an":[80],"equivalent":[81],"multichannel":[82],"over-determined":[83],"problem":[85],"properly":[88],"designed":[89],"latent":[90,97],"space.":[91],"The":[92],"space":[98],"treated":[100],"as":[101],"finding":[102],"block-wise":[105],"disentangled":[106],"representation":[107],"of":[108,122,144,174,177],"mixture.":[110],"show":[112],"empirically,":[113],"design":[116],"choices":[117],"formulation":[121],"at":[125],"hand":[126],"motivated":[127],"by":[128],"results":[134],"lead":[135],"robustness":[137],"unseen":[139],"out-of-distribution":[140],"data":[141],"reduction":[143],"overfitting":[146],"risk.":[147],"To":[148],"address":[149],"resulting":[151],"permutation":[152,160],"issue":[153],"explicitly":[155],"incorporate":[156],"novel":[158],"differentiable":[159],"loss":[161],"function":[162],"augment":[164],"model":[166],"with":[167],"memory":[169],"mechanism":[170],"keep":[172],"track":[173],"statistics":[176],"individual":[179],"sources.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}