{"id":"https://openalex.org/W3095339269","doi":"https://doi.org/10.1109/icassp39728.2021.9414003","title":"One-Shot Conditional Audio Filtering of Arbitrary Sounds","display_name":"One-Shot Conditional Audio Filtering of Arbitrary Sounds","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3095339269","doi":"https://doi.org/10.1109/icassp39728.2021.9414003","mag":"3095339269"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.02421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002559095","display_name":"Beat Gfeller","orcid":"https://orcid.org/0000-0002-1321-9015"},"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":"Beat Gfeller","raw_affiliation_strings":["Google Research","Google Research,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011258273","display_name":"Dominik Roblek","orcid":"https://orcid.org/0000-0002-2155-450X"},"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":"Dominik Roblek","raw_affiliation_strings":["Google Research","Google Research,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033341878","display_name":"Marco Tagliasacchi","orcid":"https://orcid.org/0000-0002-7682-6795"},"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":"Marco Tagliasacchi","raw_affiliation_strings":["Google Research","Google Research,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.3622,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45894388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"501","last_page":"505"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/embedding","display_name":"Embedding","score":0.712039589881897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6706754565238953},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6195052266120911},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6101527214050293},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5086908936500549},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.506611704826355},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4819895625114441},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4655979573726654},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4422568082809448},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42928919196128845},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4121135175228119},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30833059549331665},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09189975261688232},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0832863450050354}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.712039589881897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6706754565238953},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6195052266120911},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6101527214050293},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5086908936500549},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.506611704826355},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4819895625114441},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4655979573726654},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4422568082809448},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42928919196128845},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4121135175228119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30833059549331665},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09189975261688232},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0832863450050354},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414003","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.02421","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02421","pdf_url":"https://arxiv.org/pdf/2011.02421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3095339269","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.02421.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.02421","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.02421","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/ddyj-a984","is_oa":true,"landing_page_url":"https://doi.org/10.17023/ddyj-a984","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.02421","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02421","pdf_url":"https://arxiv.org/pdf/2011.02421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095339269.pdf","grobid_xml":"https://content.openalex.org/works/W3095339269.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W2031647436","https://openalex.org/W2187089797","https://openalex.org/W2593116425","https://openalex.org/W2760103357","https://openalex.org/W2795783309","https://openalex.org/W2898963093","https://openalex.org/W2900368655","https://openalex.org/W2944338086","https://openalex.org/W2950527759","https://openalex.org/W2951130829","https://openalex.org/W2963285578","https://openalex.org/W2964058413","https://openalex.org/W2970844204","https://openalex.org/W2973062255","https://openalex.org/W2981816492","https://openalex.org/W2984935418","https://openalex.org/W2990666817","https://openalex.org/W2998657200","https://openalex.org/W3000389243","https://openalex.org/W3004910802","https://openalex.org/W3008880747","https://openalex.org/W3036069164","https://openalex.org/W3046970875","https://openalex.org/W3047154545","https://openalex.org/W3083533149","https://openalex.org/W3090388844","https://openalex.org/W3095095816","https://openalex.org/W3104704316","https://openalex.org/W3165246035","https://openalex.org/W4289665794","https://openalex.org/W6639532686","https://openalex.org/W6639824700","https://openalex.org/W6684821475","https://openalex.org/W6685562342","https://openalex.org/W6734260513","https://openalex.org/W6740674931","https://openalex.org/W6749954789","https://openalex.org/W6751512325","https://openalex.org/W6766938422","https://openalex.org/W6767367760","https://openalex.org/W6771763809","https://openalex.org/W6774687970","https://openalex.org/W6779963951","https://openalex.org/W6781251213","https://openalex.org/W6803017749","https://openalex.org/W6862698496","https://openalex.org/W6891901120"],"related_works":["https://openalex.org/W3160972914","https://openalex.org/W3104704316","https://openalex.org/W1819491323","https://openalex.org/W3095868011","https://openalex.org/W3015973934","https://openalex.org/W2986060980","https://openalex.org/W2981816492","https://openalex.org/W3014036488","https://openalex.org/W3187219273","https://openalex.org/W2771189179","https://openalex.org/W3166270999","https://openalex.org/W2184670865","https://openalex.org/W3177975252","https://openalex.org/W3160191260","https://openalex.org/W2019369081","https://openalex.org/W2997738447","https://openalex.org/W3098319575","https://openalex.org/W3195078414","https://openalex.org/W3089710176","https://openalex.org/W3137586311"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,21,25,56,60,82,126,130,139],"problem":[3],"of":[4,20,91,96,109,119],"separating":[5,113],"a":[6,11,17,30,38,47,117],"particular":[7],"sound":[8,43,69],"source":[9,23,57],"from":[10,116],"single-channel":[12],"mixture,":[13],"based":[14],"on":[15,81,101],"only":[16],"short":[18],"sample":[19],"target":[22],"(from":[24],"same":[26],"recording).":[27],"Using":[28,46],"SoundFilter,":[29],"wave-to-wave":[31],"neural":[32],"network":[33],"architecture,":[34],"we":[35,123],"can":[36,63],"train":[37],"model":[39,50,62,86,104],"without":[40,147],"using":[41,148],"any":[42,149],"class":[44],"labels.":[45,150],"conditioning":[48,131],"encoder":[49,132],"which":[51],"is":[52,145],"learned":[53,128],"jointly":[54],"with":[55],"separation":[58],"network,":[59],"trained":[61,100,146],"be":[64],"\"configured\"":[65],"to":[66],"filter":[67],"arbitrary":[68],"sources,":[70],"even":[71,142],"ones":[72],"that":[73,125],"it":[74,144],"has":[75],"not":[76],"seen":[77],"during":[78],"training.":[79],"Evaluated":[80],"FSD50k":[83],"dataset,":[84],"our":[85,103],"obtains":[87],"an":[88,106],"SI-SDR":[89,107],"improvement":[90,108],"9.6":[92],"dB":[93,111],"for":[94],"mixtures":[95],"two":[97,120],"sounds.":[98],"When":[99],"Librispeech,":[102],"achieves":[105],"14.0":[110],"when":[112],"one":[114],"voice":[115],"mixture":[118],"speakers.":[121],"Moreover,":[122],"show":[124],"representation":[127],"by":[129],"clusters":[133],"acoustically":[134],"similar":[135],"sounds":[136],"together":[137],"in":[138],"embedding":[140],"space,":[141],"though":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}