{"id":"https://openalex.org/W4391021760","doi":"https://doi.org/10.1109/asru57964.2023.10389752","title":"Exploring Time-Frequency Domain Target Speaker Extraction For Causal and Non-Causal Processing","display_name":"Exploring Time-Frequency Domain Target Speaker Extraction For Causal and Non-Causal Processing","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021760","doi":"https://doi.org/10.1109/asru57964.2023.10389752"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069427874","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-8022-2142"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["Samsung Research China – Beijing (SRC-B)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research China – Beijing (SRC-B)","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9998000264167786,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7932866215705872},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7499736547470093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6332100629806519},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5707302093505859},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.5602888464927673},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5252813100814819},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5157056450843811},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4893600344657898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4632412791252136},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4408693313598633},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.41954344511032104},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4142459034919739},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.41347506642341614},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08411648869514465},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.073189377784729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932866215705872},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7499736547470093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6332100629806519},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5707302093505859},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.5602888464927673},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5252813100814819},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5157056450843811},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4893600344657898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4632412791252136},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4408693313598633},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.41954344511032104},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4142459034919739},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.41347506642341614},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08411648869514465},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.073189377784729},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1991139021","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2794289187","https://openalex.org/W2802023636","https://openalex.org/W2938646939","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2964238697","https://openalex.org/W2972541922","https://openalex.org/W2973062255","https://openalex.org/W3008003372","https://openalex.org/W3015199127","https://openalex.org/W3015623828","https://openalex.org/W3015636705","https://openalex.org/W3015834770","https://openalex.org/W3016361963","https://openalex.org/W3027008958","https://openalex.org/W3096893582","https://openalex.org/W3097653961","https://openalex.org/W3097797867","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3105928222","https://openalex.org/W3151851237","https://openalex.org/W3163652268","https://openalex.org/W3198234746","https://openalex.org/W3198543387","https://openalex.org/W3198667862","https://openalex.org/W3213661887","https://openalex.org/W4224936432","https://openalex.org/W4296070363","https://openalex.org/W4311000453","https://openalex.org/W4372260086","https://openalex.org/W4372271325","https://openalex.org/W4372271367","https://openalex.org/W4375869119","https://openalex.org/W6777776875","https://openalex.org/W6779944756","https://openalex.org/W6799838802","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4387678054","https://openalex.org/W3000097931","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W2354322770","https://openalex.org/W4226054107","https://openalex.org/W4306784355","https://openalex.org/W4237547500"],"abstract_inverted_index":{"In":[0,45,81],"recent":[1,28],"years,":[2],"target":[3,100],"speaker":[4,73,93,101],"extraction":[5],"(TSE)":[6],"has":[7],"drawn":[8],"increasing":[9],"interest":[10],"as":[11],"an":[12],"alternative":[13],"to":[14,30,50,56,83,97],"speech":[15,62],"separation":[16,63],"in":[17,27,137],"realistic":[18],"applications.":[19],"While":[20],"time-domain":[21,135],"methods":[22,40,76],"have":[23,41],"been":[24,42],"widely":[25],"used":[26],"studies":[29],"achieve":[31],"high":[32],"performance,":[33],"the":[34,58,66,78,84,99,107,122,133],"potential":[35],"of":[36],"time-frequency":[37],"(T-F)":[38],"domain":[39,61],"less":[43],"explored.":[44],"this":[46,52],"paper,":[47],"we":[48,89,104],"try":[49],"fill":[51],"gap":[53],"and":[54,124,140],"propose":[55,90],"incorporate":[57],"top-performing":[59],"T-F":[60],"method":[64,96],"into":[65],"TSE":[67],"framework.":[68],"We":[69],"first":[70],"explore":[71],"different":[72],"information":[74],"fusion":[75,95],"for":[77,114],"proposed":[79,108,130],"model.":[80],"addition":[82],"commonly-used":[85],"concatenation":[86],"based":[87],"fusion,":[88],"a":[91,144],"novel":[92],"token-based":[94],"fuse":[98],"information.":[102],"Second,":[103],"show":[105,127],"that":[106,128],"model":[109,131],"can":[110],"be":[111],"easily":[112],"extended":[113],"causal":[115,139],"processing":[116],"with":[117],"strong":[118],"performance.":[119],"Experiments":[120],"on":[121],"WSJ0-2mix":[123],"LibriMix":[125],"benchmarks":[126],"our":[129],"outperforms":[132],"widely-used":[134],"models":[136],"both":[138],"non-causal":[141],"settings":[142],"by":[143],"large":[145],"margin.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}