{"id":"https://openalex.org/W2735663686","doi":"https://doi.org/10.1109/taslp.2018.2795749","title":"Speaker-Independent Speech Separation With Deep Attractor Network","display_name":"Speaker-Independent Speech Separation With Deep Attractor Network","publication_year":2018,"publication_date":"2018-01-19","ids":{"openalex":"https://openalex.org/W2735663686","doi":"https://doi.org/10.1109/taslp.2018.2795749","mag":"2735663686"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2795749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2795749","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1707.03634","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048439332"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":29.2733,"has_fulltext":false,"cited_by_count":271,"citation_normalized_percentile":{"value":0.9981772,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"26","issue":"4","first_page":"787","last_page":"796"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/separation","display_name":"Separation (statistics)","score":0.6519791483879089},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6094465255737305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5694902539253235},{"id":"https://openalex.org/keywords/attractor","display_name":"Attractor","score":0.4308621287345886},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41574597358703613},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35803890228271484},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1286904513835907},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.04609796404838562}],"concepts":[{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6519791483879089},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6094465255737305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5694902539253235},{"id":"https://openalex.org/C164380108","wikidata":"https://www.wikidata.org/wiki/Q507187","display_name":"Attractor","level":2,"score":0.4308621287345886},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41574597358703613},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35803890228271484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1286904513835907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.04609796404838562},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2018.2795749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2795749","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1707.03634","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.03634","pdf_url":"https://arxiv.org/pdf/1707.03634","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":"pmh:oai:arXiv.org:1707.03634","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1707.03634","pdf_url":"https://arxiv.org/pdf/1707.03634","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"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G7827343844","display_name":null,"funder_award_id":"DC014279","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320306148","display_name":"Pew Charitable Trusts","ror":"https://ror.org/02xhk2825"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1485161427","https://openalex.org/W1522301498","https://openalex.org/W1524678615","https://openalex.org/W1552314771","https://openalex.org/W1780344239","https://openalex.org/W1790748249","https://openalex.org/W1977556410","https://openalex.org/W1991112797","https://openalex.org/W2019129540","https://openalex.org/W2053186076","https://openalex.org/W2064675550","https://openalex.org/W2082183045","https://openalex.org/W2088361146","https://openalex.org/W2095705004","https://openalex.org/W2098882755","https://openalex.org/W2103091632","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2129116669","https://openalex.org/W2135029798","https://openalex.org/W2140679639","https://openalex.org/W2141411743","https://openalex.org/W2147174722","https://openalex.org/W2147455188","https://openalex.org/W2150389998","https://openalex.org/W2150415460","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2159202424","https://openalex.org/W2160201556","https://openalex.org/W2165874743","https://openalex.org/W2168379380","https://openalex.org/W2187089797","https://openalex.org/W2221409856","https://openalex.org/W2289731793","https://openalex.org/W2296073425","https://openalex.org/W2304609584","https://openalex.org/W2345067732","https://openalex.org/W2405258286","https://openalex.org/W2405774341","https://openalex.org/W2460742184","https://openalex.org/W2465050681","https://openalex.org/W2533523411","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2561557072","https://openalex.org/W2573611911","https://openalex.org/W2609317876","https://openalex.org/W2708109968","https://openalex.org/W2734774145","https://openalex.org/W2755891984","https://openalex.org/W2962715207","https://openalex.org/W2962883855","https://openalex.org/W2964121744","https://openalex.org/W2998704965","https://openalex.org/W3124794156","https://openalex.org/W3143596294","https://openalex.org/W4285719527","https://openalex.org/W4294170691","https://openalex.org/W6623987585","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6679489070","https://openalex.org/W6680012447","https://openalex.org/W6680532216","https://openalex.org/W6681474505","https://openalex.org/W6682691769","https://openalex.org/W6684578312","https://openalex.org/W6713658392","https://openalex.org/W6713676406","https://openalex.org/W6728841359","https://openalex.org/W6731969710","https://openalex.org/W6744261651"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Despite":[0],"the":[1,26,30,36,41,44,50,78,82,97,108,111,114,129,138,142,150,156,169,191],"recent":[2],"success":[3],"of":[4,29,47,68,81,110,120,141],"deep":[5,59,212],"learning":[6,60,213],"for":[7,18,62,148,152,168,215],"many":[8],"speech":[9,14,63,216],"processing":[10],"tasks,":[11],"single-microphone,":[12],"speaker-independent":[13],"separation":[15,64],"remains":[16],"challenging":[17],"two":[19,198],"main":[20],"reasons.":[21],"The":[22,117,165],"first":[23],"reason":[24],"is":[25,43,94,105,134,171],"arbitrary":[27],"order":[28],"target":[31],"and":[32,40,159,163,183,199,203],"masker":[33],"speakers":[34,48],"in":[35,49,96,113,155],"mixture":[37,51,83],"(permutation":[38],"problem),":[39],"second":[42],"unknown":[45],"number":[46],"(output":[52],"dimension":[53],"problem).":[54],"We":[55,71,144,186],"propose":[56,145],"a":[57,73,86],"novel":[58],"framework":[61],"that":[65],"addresses":[66],"both":[67,181],"these":[69],"issues.":[70],"use":[72],"neural":[74],"network":[75,170],"to":[76,100,126,136],"project":[77],"time-frequency":[79,118,139],"representation":[80],"signal":[84,173],"into":[85],"high-dimensional":[87],"embedding":[88,98,115,157],"space.":[89,116],"A":[90],"reference":[91],"point":[92,132],"(attractor)":[93],"created":[95],"space":[99,158],"represent":[101],"each":[102,121,153],"speaker":[103,112,122,201],"which":[104,133,176],"defined":[106],"as":[107],"centroid":[109],"embeddings":[119],"are":[123],"then":[124],"forced":[125],"cluster":[127],"around":[128],"corresponding":[130],"attractor":[131],"used":[135],"determine":[137],"assignment":[140],"speaker.":[143],"three":[146,200],"methods":[147,214],"finding":[149],"attractors":[151],"source":[154],"compare":[160],"their":[161],"advantages":[162],"limitations.":[164],"objective":[166],"function":[167],"standard":[172],"reconstruction":[174],"error":[175],"enables":[177],"end-to-end":[178],"operation":[179],"during":[180],"training":[182],"test":[184],"phases.":[185],"evaluated":[187],"our":[188],"system":[189],"using":[190],"Wall":[192],"Street":[193],"Journal":[194],"dataset":[195],"(WSJ0)":[196],"on":[197],"mixtures":[202],"report":[204],"comparable":[205],"or":[206],"better":[207],"performance":[208],"than":[209],"other":[210],"state-of-the-art":[211],"separation.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":42},{"year":2020,"cited_by_count":59},{"year":2019,"cited_by_count":55},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}