{"id":"https://openalex.org/W4289665794","doi":"https://doi.org/10.1145/3197517.3201357","title":"Looking to listen at the cocktail party","display_name":"Looking to listen at the cocktail party","publication_year":2018,"publication_date":"2018-07-30","ids":{"openalex":"https://openalex.org/W4289665794","doi":"https://doi.org/10.1145/3197517.3201357"},"language":"en","primary_location":{"id":"doi:10.1145/3197517.3201357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3197517.3201357","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3197517.3201357","source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3197517.3201357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012422543","display_name":"Ariel Ephrat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117425","display_name":"Google (Israel)","ror":"https://ror.org/02c20ys54","country_code":"IL","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210117425","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Ariel Ephrat","raw_affiliation_strings":["Google Research and The Hebrew University of Jerusalem, Israel"],"affiliations":[{"raw_affiliation_string":"Google Research and The Hebrew University of Jerusalem, Israel","institution_ids":["https://openalex.org/I4210117425","https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068842079","display_name":"Inbar Mosseri","orcid":"https://orcid.org/0000-0001-8757-7790"},"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":"Inbar Mosseri","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035078692","display_name":"Oran Lang","orcid":"https://orcid.org/0000-0001-7644-8459"},"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":"Oran Lang","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058866986","display_name":"Tali Dekel","orcid":"https://orcid.org/0000-0003-3703-0783"},"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":"Tali Dekel","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","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"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089579452","display_name":"Avinatan Hassidim","orcid":"https://orcid.org/0000-0002-3855-344X"},"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":"Avinatan Hassidim","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074429265","display_name":"William T. Freeman","orcid":"https://orcid.org/0000-0002-2231-7995"},"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":"William T. Freeman","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007681620","display_name":"Michael Rubinstein","orcid":"https://orcid.org/0000-0002-3707-3807"},"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":"Michael Rubinstein","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5012422543"],"corresponding_institution_ids":["https://openalex.org/I197251160","https://openalex.org/I4210117425"],"apc_list":null,"apc_paid":null,"fwci":34.1575,"has_fulltext":true,"cited_by_count":565,"citation_normalized_percentile":{"value":0.99889452,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"37","issue":"4","first_page":"1","last_page":"11"},"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":0.9987999796867371,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.998199999332428,"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":0.8200106024742126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7144749760627747},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5800024271011353},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5094965100288391},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5016896724700928},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4838337004184723},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45124951004981995},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4425828456878662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3215438425540924},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2449420988559723},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11062905192375183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8200106024742126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7144749760627747},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5800024271011353},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5094965100288391},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5016896724700928},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4838337004184723},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45124951004981995},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4425828456878662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3215438425540924},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2449420988559723},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11062905192375183},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3197517.3201357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3197517.3201357","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3197517.3201357","source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1804.03619","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.03619","pdf_url":"https://arxiv.org/pdf/1804.03619","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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3197517.3201357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3197517.3201357","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3197517.3201357","source":{"id":"https://openalex.org/S185367456","display_name":"ACM Transactions on Graphics","issn_l":"0730-0301","issn":["0730-0301","1557-7368"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Graphics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289665794.pdf","grobid_xml":"https://content.openalex.org/works/W4289665794.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1496883935","https://openalex.org/W1503933356","https://openalex.org/W1552314771","https://openalex.org/W1755563775","https://openalex.org/W1836465849","https://openalex.org/W1849277567","https://openalex.org/W1897240248","https://openalex.org/W1899185266","https://openalex.org/W1964448421","https://openalex.org/W1971168548","https://openalex.org/W1976188834","https://openalex.org/W1991139021","https://openalex.org/W2029199293","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2081144555","https://openalex.org/W2088079940","https://openalex.org/W2099128937","https://openalex.org/W2101036994","https://openalex.org/W2101045344","https://openalex.org/W2127851351","https://openalex.org/W2128653983","https://openalex.org/W2148659689","https://openalex.org/W2167734090","https://openalex.org/W2168010845","https://openalex.org/W2184188583","https://openalex.org/W2221409856","https://openalex.org/W2311038409","https://openalex.org/W2460742184","https://openalex.org/W2495705551","https://openalex.org/W2525694994","https://openalex.org/W2532854561","https://openalex.org/W2556930864","https://openalex.org/W2593116425","https://openalex.org/W2598036111","https://openalex.org/W2605589342","https://openalex.org/W2621109248","https://openalex.org/W2660943524","https://openalex.org/W2730845691","https://openalex.org/W2735090526","https://openalex.org/W2750143381","https://openalex.org/W2771039075","https://openalex.org/W2788241093","https://openalex.org/W2796992393","https://openalex.org/W2952746495","https://openalex.org/W2962715207","https://openalex.org/W2962865004","https://openalex.org/W2962866211","https://openalex.org/W2962960500","https://openalex.org/W2963019222","https://openalex.org/W2963218389","https://openalex.org/W2963812294","https://openalex.org/W2964171275","https://openalex.org/W3105024549","https://openalex.org/W3105099157","https://openalex.org/W3127686677","https://openalex.org/W4302114989","https://openalex.org/W4307196995"],"related_works":["https://openalex.org/W2012531322","https://openalex.org/W2785900585","https://openalex.org/W2353730437","https://openalex.org/W2490303674","https://openalex.org/W1630865680","https://openalex.org/W1996130883","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"We":[0,118],"present":[1,55],"a":[2,8,13,56,84,104,205],"joint":[3,96],"audio-visual":[4,97,196],"model":[5,59,207],"for":[6,208],"isolating":[7],"single":[9],"speech":[10,44,90,127,158,171,197],"signal":[11],"from":[12,115],"mixture":[14],"of":[15,41,108,110,112,122,151,175,211],"sounds":[16],"such":[17],"as":[18,30,130,132],"other":[19],"speakers":[20,47,82],"and":[21,35,64,86,140],"background":[22],"noise.":[23],"Solving":[24],"this":[25,52,69],"task":[26],"using":[27],"only":[28,143],"audio":[29,79],"input":[31],"is":[32,183],"extremely":[33],"challenging":[34],"does":[36],"not":[37],"provide":[38],"an":[39],"association":[40],"the":[42,49,78,89,116,120,145,149,152,155],"separated":[43],"signals":[45,66],"with":[46],"in":[48,83,154,173],"video.":[50],"In":[51,178],"paper,":[53],"we":[54,99],"deep":[57],"network-based":[58],"that":[60,200],"incorporates":[61],"both":[62],"visual":[63,72],"auditory":[65],"to":[67,76,87,125,147,161,188],"solve":[68],"task.":[70],"The":[71],"features":[73],"are":[74,201],"used":[75],"\"focus\"":[77],"on":[80],"desired":[81],"scene":[85],"improve":[88],"separation":[91,128,172,198],"quality.":[92],"To":[93],"train":[94],"our":[95,123,180],"model,":[98,181],"introduce":[100],"AVS":[101],"peech":[102],",":[103],"new":[105],"dataset":[106],"comprised":[107],"thousands":[109],"hours":[111],"video":[113,156],"segments":[114],"Web.":[117],"demonstrate":[119],"applicability":[121],"method":[124,164],"classic":[126],"tasks,":[129],"well":[131],"real-world":[133],"scenarios":[134],"involving":[135],"heated":[136],"interviews,":[137],"noisy":[138],"bars,":[139],"screaming":[141],"children,":[142],"requiring":[144],"user":[146],"specify":[148],"face":[150],"person":[153],"whose":[157],"they":[159],"want":[160],"isolate.":[162],"Our":[163],"shows":[165],"clear":[166],"advantage":[167],"over":[168],"state-of-the-art":[169],"audio-only":[170],"cases":[174],"mixed":[176],"speech.":[177],"addition,":[179],"which":[182],"speaker-independent":[184],"(trained":[185],"once,":[186],"applicable":[187],"any":[189],"speaker),":[190],"produces":[191],"better":[192],"results":[193],"than":[194],"recent":[195],"methods":[199],"speaker-dependent":[202],"(require":[203],"training":[204],"separate":[206],"each":[209],"speaker":[210],"interest).":[212]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":78},{"year":2024,"cited_by_count":89},{"year":2023,"cited_by_count":96},{"year":2022,"cited_by_count":83},{"year":2021,"cited_by_count":95},{"year":2020,"cited_by_count":63},{"year":2019,"cited_by_count":42},{"year":2018,"cited_by_count":6}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2022-08-03T00:00:00"}