{"id":"https://openalex.org/W2944338086","doi":"https://doi.org/10.1109/waspaa.2019.8937253","title":"Universal Sound Separation","display_name":"Universal Sound Separation","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2944338086","doi":"https://doi.org/10.1109/waspaa.2019.8937253","mag":"2944338086"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2019.8937253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.03330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052656596","display_name":"Ilya Kavalerov","orcid":"https://orcid.org/0000-0002-9733-0190"},"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":true,"raw_author_name":"Ilya Kavalerov","raw_affiliation_strings":["Google Research, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"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, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"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":"Hakan Erdogan","raw_affiliation_strings":["Google Research, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013234773","display_name":"Brian Patton","orcid":"https://orcid.org/0000-0001-8222-4419"},"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":"Brian Patton","raw_affiliation_strings":["Google Research, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"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":"Kevin Wilson","raw_affiliation_strings":["Google Research, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA","[Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA]"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"[Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA]","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","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, Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Google Research, Cambridge, MA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5052656596"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.3397,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80992795,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"179"},"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":0.9991000294685364,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7196759581565857},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6077024936676025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5830633044242859},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5318690538406372},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.479248046875},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.42613735795021057},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3322543501853943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27428966760635376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1623193323612213},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1318330466747284},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11837124824523926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196759581565857},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6077024936676025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5830633044242859},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5318690538406372},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.479248046875},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.42613735795021057},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3322543501853943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27428966760635376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1623193323612213},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1318330466747284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11837124824523926},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","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},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/waspaa.2019.8937253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.03330","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03330","pdf_url":"https://arxiv.org/pdf/1905.03330","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:2944338086","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1905.03330","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.1905.03330","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.03330","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.03330","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03330","pdf_url":"https://arxiv.org/pdf/1905.03330","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944338086.pdf","grobid_xml":"https://content.openalex.org/works/W2944338086.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1897240248","https://openalex.org/W2031647436","https://openalex.org/W2046869671","https://openalex.org/W2078528584","https://openalex.org/W2101045344","https://openalex.org/W2221409856","https://openalex.org/W2401387233","https://openalex.org/W2405774341","https://openalex.org/W2460742184","https://openalex.org/W2552071709","https://openalex.org/W2587994092","https://openalex.org/W2605138598","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2749131051","https://openalex.org/W2774707525","https://openalex.org/W2793043762","https://openalex.org/W2891405874","https://openalex.org/W2907121943","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2963189033","https://openalex.org/W2963751183","https://openalex.org/W2963816101","https://openalex.org/W2963902628","https://openalex.org/W2964058413","https://openalex.org/W2964136284","https://openalex.org/W6631190155","https://openalex.org/W6639532686","https://openalex.org/W6713658392","https://openalex.org/W6733667431","https://openalex.org/W6743462201","https://openalex.org/W6746914816","https://openalex.org/W6749620070","https://openalex.org/W6752109149","https://openalex.org/W6754743415","https://openalex.org/W6756381845","https://openalex.org/W6757468910"],"related_works":["https://openalex.org/W2998657200","https://openalex.org/W2952218014","https://openalex.org/W2892365986","https://openalex.org/W2994988791","https://openalex.org/W3209238651","https://openalex.org/W2221409856","https://openalex.org/W2127851351","https://openalex.org/W3132015784","https://openalex.org/W2941619235","https://openalex.org/W3015654783","https://openalex.org/W2288838913","https://openalex.org/W2994785103","https://openalex.org/W3031135612","https://openalex.org/W2181635884","https://openalex.org/W3199713199","https://openalex.org/W3098606562","https://openalex.org/W2948661109","https://openalex.org/W2514426326","https://openalex.org/W3090699804","https://openalex.org/W3089552252"],"abstract_inverted_index":{"Recent":[0],"deep":[1],"learning":[2],"approaches":[3,16],"have":[4,17],"achieved":[5],"impressive":[6],"performance":[7,44],"on":[8,45,200],"speech":[9,46],"enhancement":[10,111],"and":[11,39,66,83,100,144,229],"separation":[12,75,127,228],"tasks.":[13,52,202],"However,":[14],"these":[15,155],"not":[18],"been":[19],"investigated":[20],"for":[21,88,167,178,188,204,226,234],"separating":[22],"mixtures":[23,62],"of":[24,27,61,73,109,131,154,162,222],"arbitrary":[25,64,189],"sounds":[26],"different":[28],"types,":[29],"a":[30,59,139,145],"task":[31],"we":[32,57,119,136,157,169],"refer":[33],"to":[34,50,69,231],"as":[35,148],"universal":[36,205,235],"sound":[37,206,236],"separation,":[38,180,207],"it":[40,68],"is":[41],"unknown":[42],"how":[43],"tasks":[47],"carries":[48],"over":[49,223],"non-speech":[51],"To":[53],"study":[54],"this":[55],"question,":[56],"develop":[58],"dataset":[60],"containing":[63],"sounds,":[65],"use":[67],"investigate":[70],"the":[71,79,84,106,116,132,160],"space":[72],"mask-based":[74],"architectures,":[76],"varying":[77],"both":[78,138,153],"overall":[80],"network":[81,92],"architecture":[82],"framewise":[85],"analysis-synthesis":[86,134],"basis":[87],"signal":[89],"transformations.":[90],"These":[91],"architectures":[93],"include":[94],"convolutional":[95],"long":[96],"short-term":[97],"memory":[98],"networks":[99,112],"time-dilated":[101],"convolution":[102],"stacks":[103],"inspired":[104],"by":[105],"recent":[107],"success":[108],"time-domain":[110],"like":[113],"ConvTasNet.":[114,151],"For":[115,152,191],"latter":[117],"architecture,":[118],"also":[120,158],"propose":[121],"novel":[122],"modifications":[123],"that":[124,171],"further":[125],"improve":[126],"performance.":[128],"In":[129,165],"terms":[130],"frame-wise":[133],"basis,":[135,147],"explore":[137],"short-time":[140],"Fourier":[141],"transform":[142],"(STFT)":[143],"learnable":[146,192,210],"used":[149],"in":[150,218],"bases,":[156,193],"examine":[159],"effect":[161],"window":[163],"size.":[164],"particular,":[166],"STFTs,":[168],"find":[170],"longer":[172],"windows":[173,183,195],"(25-50":[174],"ms)":[175,185,197],"work":[176,186,198],"best":[177,187,199,213],"speech/non-speech":[179,227],"while":[181],"shorter":[182,194],"(2.5":[184,196],"sounds.":[190],"all":[201],"Surprisingly,":[203],"STFTs":[208],"outperform":[209],"bases.":[211],"Our":[212],"methods":[214],"produce":[215],"an":[216],"improvement":[217],"scale-invariant":[219],"signal-to-distortion":[220],"ratio":[221],"13":[224],"dB":[225,233],"close":[230],"10":[232],"separation.":[237]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}