{"id":"https://openalex.org/W4385477789","doi":"https://doi.org/10.1109/icasspw59220.2023.10193208","title":"Audioslots: A Slot-Centric Generative Model For Audio Separation","display_name":"Audioslots: A Slot-Centric Generative Model For Audio Separation","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385477789","doi":"https://doi.org/10.1109/icasspw59220.2023.10193208"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5111126172","display_name":"Pradyumna Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pradyumna Reddy","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082808731","display_name":"Klaus Greff","orcid":"https://orcid.org/0000-0001-6982-0937"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Klaus Greff","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025691113","display_name":"Thomas Kipf","orcid":"https://orcid.org/0000-0003-4486-409X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Kipf","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8068318367004395},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6555115580558777},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.606406033039093},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5136589407920837},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5091473460197449},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4696072041988373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4667872190475464},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.45546776056289673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44116392731666565},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4352447986602783},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.43396273255348206},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.43247273564338684},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.42243391275405884},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30536752939224243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8068318367004395},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6555115580558777},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.606406033039093},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5136589407920837},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5091473460197449},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4696072041988373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4667872190475464},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.45546776056289673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44116392731666565},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4352447986602783},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.43396273255348206},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.43247273564338684},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.42243391275405884},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30536752939224243},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2046869671","https://openalex.org/W2147455188","https://openalex.org/W2194775991","https://openalex.org/W2221409856","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2913954345","https://openalex.org/W2919112510","https://openalex.org/W2952218014","https://openalex.org/W2953116911","https://openalex.org/W2953273646","https://openalex.org/W2962715207","https://openalex.org/W2963716836","https://openalex.org/W2964058413","https://openalex.org/W2998490864","https://openalex.org/W3015199127","https://openalex.org/W3027008958","https://openalex.org/W3036843665","https://openalex.org/W3037784242","https://openalex.org/W3040538742","https://openalex.org/W3093839391","https://openalex.org/W3095095816","https://openalex.org/W3099330747","https://openalex.org/W3109585842","https://openalex.org/W3163652268","https://openalex.org/W3177067699","https://openalex.org/W4226246634","https://openalex.org/W4282913091","https://openalex.org/W4285483774","https://openalex.org/W4300978696","https://openalex.org/W4307478915","https://openalex.org/W4312819586","https://openalex.org/W4318242507","https://openalex.org/W4372271367","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6685265622","https://openalex.org/W6739901393","https://openalex.org/W6744580074","https://openalex.org/W6755477022","https://openalex.org/W6758665762","https://openalex.org/W6759669191","https://openalex.org/W6764556126","https://openalex.org/W6777776875","https://openalex.org/W6779809370","https://openalex.org/W6780179280","https://openalex.org/W6781147418","https://openalex.org/W6784499681","https://openalex.org/W6804342959","https://openalex.org/W6839133533","https://openalex.org/W6842384739","https://openalex.org/W6843330092","https://openalex.org/W6844662008","https://openalex.org/W6846419837","https://openalex.org/W6849002408"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W1509813908","https://openalex.org/W2898606530","https://openalex.org/W2098101267","https://openalex.org/W2059119686","https://openalex.org/W4289362680","https://openalex.org/W2403380333"],"abstract_inverted_index":{"In":[0],"a":[1,29,61,97,109],"range":[2],"of":[3,69,111,124],"recent":[4],"works,":[5],"object-centric":[6],"architectures":[7],"have":[8],"been":[9],"shown":[10],"to":[11,59,65,79,134],"be":[12],"suitable":[13],"for":[14,33,140],"unsupervised":[15],"scene":[16],"decomposition":[17],"in":[18,37,92,127],"the":[19,38,55,81,85,90,120,136],"vision":[20],"domain.":[21,40],"Inspired":[22],"by":[23],"these":[24],"methods":[25],"we":[26],"present":[27],"AudioSlots,":[28],"slot-centric":[30],"generative":[31],"model":[32,91],"blind":[34],"source":[35,71,82,86],"separation":[36,107],"audio":[39,63],"AudioSlots":[41],"is":[42],"built":[43],"using":[44,96],"permutation-equivariant":[45],"encoder":[46,51],"and":[47,122,129,138],"decoder":[48,76],"networks.":[49],"The":[50,73],"network":[52,77],"based":[53],"on":[54,104],"Transformer":[56],"architecture":[57],"learns":[58,78],"map":[60],"mixed":[62],"spectrogram":[64],"an":[66,93],"unordered":[67],"set":[68],"independent":[70],"embeddings.":[72,87],"spatial":[74],"broadcast":[75],"generate":[80],"spectrograms":[83],"from":[84],"We":[88,118],"train":[89],"end-to-end":[94],"manner":[95],"permutation":[98],"invariant":[99],"loss":[100],"function.":[101],"Our":[102],"results":[103,121],"Libri2Mix":[105],"speech":[106],"constitute":[108],"proof":[110],"concept":[112],"that":[113],"this":[114],"approach":[115,126],"shows":[116],"promise.":[117],"discuss":[119],"limitations":[123,137],"our":[125],"detail,":[128],"further":[130],"outline":[131],"potential":[132],"ways":[133],"overcome":[135],"directions":[139],"future":[141],"work.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}