{"id":"https://openalex.org/W2964238697","doi":"https://doi.org/10.21437/interspeech.2018-1205","title":"Deep Extractor Network for Target Speaker Recovery from Single Channel Speech Mixtures","display_name":"Deep Extractor Network for Target Speaker Recovery from Single Channel Speech Mixtures","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2964238697","doi":"https://doi.org/10.21437/interspeech.2018-1205","mag":"2964238697"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1205","doi":"https://doi.org/10.21437/interspeech.2018-1205","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1205","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1807.08974","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110195480","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-8932-6661","observed_orcids":["https://orcid.org/0000-0001-8932-6661","https://orcid.org/0009-0006-2077-7513"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545","observed_orcids":["https://orcid.org/0000-0001-5746-9545"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072495935","display_name":"Lianwu Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lianwu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407019","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0002-0031-9156","observed_orcids":["https://orcid.org/0000-0002-0031-9156"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790","observed_orcids":["https://orcid.org/0000-0002-0314-3790"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844","observed_orcids":["https://orcid.org/0000-0003-0520-6844"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue WA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.9392,"has_fulltext":true,"cited_by_count":82,"citation_normalized_percentile":{"value":0.99245806,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"307","last_page":"311"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9369999766349792,"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":0.9369999766349792,"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":0.05490000173449516,"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":0.005900000222027302,"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/single-channel-speech-separation","display_name":"single-channel speech separation","score":0.8790000081062317},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.6299999952316284},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974760890007019},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.6843733787536621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5902794599533081},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5596144199371338},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2826147973537445},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11861112713813782},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1205","doi":"https://doi.org/10.21437/interspeech.2018-1205","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1205","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1807.08974","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.08974","pdf_url":"https://arxiv.org/pdf/1807.08974","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.1807.08974","doi":"https://doi.org/10.48550/arxiv.1807.08974","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1807.08974","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1807.08974","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.08974","pdf_url":"https://arxiv.org/pdf/1807.08974","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,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964238697.pdf","grobid_xml":"https://content.openalex.org/works/W2964238697.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W2057826000","https://openalex.org/W2127851351","https://openalex.org/W2144763279","https://openalex.org/W2170864449","https://openalex.org/W2221409856","https://openalex.org/W2304609584","https://openalex.org/W2397725648","https://openalex.org/W2398776621","https://openalex.org/W2460742184","https://openalex.org/W2465050681","https://openalex.org/W2513836842","https://openalex.org/W2558649592","https://openalex.org/W2640112133","https://openalex.org/W2735006420","https://openalex.org/W2749510669","https://openalex.org/W2749659773","https://openalex.org/W2794289187","https://openalex.org/W2962728945","https://openalex.org/W2962866211","https://openalex.org/W2963773971","https://openalex.org/W2963843276","https://openalex.org/W3099832538"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1979583797","https://openalex.org/W3082848404","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2372254676","https://openalex.org/W2382290278","https://openalex.org/W2350741829"],"abstract_inverted_index":{"Speaker-aware":[0],"source":[1,13],"separation":[2],"methods":[3],"are":[4,108],"promising":[5],"workarounds":[6],"for":[7,50,102],"major":[8],"difficulties":[9],"such":[10],"as":[11,119],"arbitrary":[12],"permutation":[14],"and":[15,61,92,105,116,170,176],"unknown":[16],"number":[17],"of":[18,88],"sources.":[19],"However,":[20],"it":[21,190],"remains":[22],"challenging":[23],"to":[24,68,122,125,127,195],"achieve":[25],"satisfying":[26],"performance":[27],"provided":[28],"a":[29,40,55,112,128,146,161,181],"very":[30,147],"short":[31,148],"available":[32],"target":[33,52,70,158],"speaker":[34,53],"utterance":[35],"(anchor).":[36],"Here":[37],"we":[38,133,188],"present":[39],"novel":[41],"\"deep":[42],"extractor":[43,48],"network\"":[44],"which":[45,132,163],"creates":[46],"an":[47,96,120],"point":[49],"the":[51,64,69,82,90,93,103,138,150],"in":[54,80,111,174],"canonical":[56,83,129],"high":[57,156],"dimensional":[58],"embedding":[59,84,114,130],"space,":[60,115],"pulls":[62],"together":[63],"time-frequency":[65],"bins":[66],"corresponding":[67],"speaker.":[71,200],"The":[72],"proposed":[73,151],"model":[74,152],"is":[75],"different":[76],"from":[77,160],"prior":[78],"works":[79],"that":[81,144],"space":[85,131],"encodes":[86],"knowledges":[87],"both":[89],"anchor":[91,104],"mixture":[94,106],"during":[95],"end-to-end":[97],"training":[98],"phase:":[99],"First,":[100],"embeddings":[101],"speech":[107,159],"separately":[109],"constructed":[110],"primary":[113,139],"then":[117],"combined":[118],"input":[121],"feed-forward":[123],"layers":[124],"transform":[126],"discover":[134],"more":[135,196],"stable":[136],"than":[137,197],"one.":[140],"Experimental":[141],"results":[142],"show":[143,189],"given":[145],"utterance,":[149],"can":[153,191],"efficiently":[154],"recover":[155],"quality":[157],"mixture,":[162],"outperforms":[164],"various":[165],"baseline":[166,182],"models,":[167],"with":[168,180],"5.2%":[169],"6.6%":[171],"relative":[172],"improvements":[173],"SDR":[175],"PESQ":[177],"respectively":[178],"compared":[179],"oracle":[183],"deep":[184],"attracor":[185],"model.":[186],"Meanwhile,":[187],"be":[192],"generalized":[193],"well":[194],"one":[198],"interfering":[199]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":22}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}