{"id":"https://openalex.org/W4367597591","doi":"https://doi.org/10.1109/msp.2023.3240008","title":"Neural Target Speech Extraction: An overview","display_name":"Neural Target Speech Extraction: An overview","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W4367597591","doi":"https://doi.org/10.1109/msp.2023.3240008"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2023.3240008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2023.3240008","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"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 Signal Processing Magazine","raw_type":"journal-article"},"type":"article","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/A5067790073","display_name":"Kate\u0159ina \u017dmol\u00edkov\u00e1","orcid":"https://orcid.org/0000-0003-4438-8580"},"institutions":[{"id":"https://openalex.org/I4210091381","display_name":"William Demant Holding (Denmark)","ror":"https://ror.org/00an7pj80","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210091381"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Katerina Zmolikova","raw_affiliation_strings":["Demant, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-4438-8580","affiliations":[{"raw_affiliation_string":"Demant, Copenhagen, Denmark","institution_ids":["https://openalex.org/I4210091381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5175-7834","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2519-2032","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["Google, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan \u010cernock\u00fd","raw_affiliation_strings":["Department of Computer Graphics and Multimedia, Faculty of Information Technology (FIT), BUT, Brno, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0002-8800-0210","affiliations":[{"raw_affiliation_string":"Department of Computer Graphics and Multimedia, Faculty of Information Technology (FIT), BUT, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, USA"],"raw_orcid":"https://orcid.org/0000-0003-0520-6844","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.1898,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":{"value":0.99582566,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"40","issue":"3","first_page":"8","last_page":"29"},"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":0.9986000061035156,"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733320951461792},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.732040524482727},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6585995554924011},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6040477156639099},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.549342691898346},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5396963953971863},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4898481070995331},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4431456923484802},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4359092712402344},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4340367615222931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2952944040298462},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17382264137268066},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15273842215538025},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.13336580991744995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733320951461792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.732040524482727},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6585995554924011},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6040477156639099},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.549342691898346},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5396963953971863},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4898481070995331},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4431456923484802},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4359092712402344},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4340367615222931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2952944040298462},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17382264137268066},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15273842215538025},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.13336580991744995},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msp.2023.3240008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2023.3240008","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"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 Signal Processing Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5,"id":"https://metadata.un.org/sdg/10"},{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W2079362249","https://openalex.org/W2087368178","https://openalex.org/W2099128937","https://openalex.org/W2127851351","https://openalex.org/W2150415460","https://openalex.org/W2150769028","https://openalex.org/W2160766896","https://openalex.org/W2164637175","https://openalex.org/W2167734090","https://openalex.org/W2170864449","https://openalex.org/W2221409856","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2556699818","https://openalex.org/W2568308529","https://openalex.org/W2749510669","https://openalex.org/W2749659773","https://openalex.org/W2787692317","https://openalex.org/W2890964092","https://openalex.org/W2891833136","https://openalex.org/W2900292050","https://openalex.org/W2906289885","https://openalex.org/W2938646939","https://openalex.org/W2946521785","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962753171","https://openalex.org/W2962865004","https://openalex.org/W2962866211","https://openalex.org/W2962960500","https://openalex.org/W2963082324","https://openalex.org/W2964171275","https://openalex.org/W2965390715","https://openalex.org/W2972362771","https://openalex.org/W2972474532","https://openalex.org/W2972513594","https://openalex.org/W2972568703","https://openalex.org/W2972802573","https://openalex.org/W2973062255","https://openalex.org/W2976460547","https://openalex.org/W2981976899","https://openalex.org/W2997696598","https://openalex.org/W3008003372","https://openalex.org/W3011424113","https://openalex.org/W3015256813","https://openalex.org/W3015915076","https://openalex.org/W3024085360","https://openalex.org/W3024147341","https://openalex.org/W3025260599","https://openalex.org/W3033703941","https://openalex.org/W3057611960","https://openalex.org/W3095263845","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3105928222","https://openalex.org/W3136499730","https://openalex.org/W3138621071","https://openalex.org/W3148386121","https://openalex.org/W3160348851","https://openalex.org/W3160972914","https://openalex.org/W3161158930","https://openalex.org/W3196845798","https://openalex.org/W3206706278","https://openalex.org/W3213661887","https://openalex.org/W4210710538","https://openalex.org/W4224871700","https://openalex.org/W4247773827","https://openalex.org/W4288054834","https://openalex.org/W4289665794","https://openalex.org/W4296069305","https://openalex.org/W6675117242","https://openalex.org/W6730039835"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2562096895","https://openalex.org/W2475724061","https://openalex.org/W2333799855","https://openalex.org/W2556771176","https://openalex.org/W2640905660","https://openalex.org/W2402949781","https://openalex.org/W2122924390"],"abstract_inverted_index":{"Humans":[0],"can":[1,123],"listen":[2],"to":[3,147],"a":[4,68,72,96,106,113,144],"target":[5,48,69,104],"speaker":[6,70,88],"even":[7],"in":[8,89,138],"challenging":[9],"acoustic":[10],"conditions":[11],"that":[12,85,133],"have":[13,30],"noise,":[14],"reverberation,":[15],"and":[16,49,81,112,152,162,177,197],"interfering":[17,44],"speakers.":[18],"This":[19,170],"phenomenon":[20],"is":[21,42,127],"known":[22],"as":[23,159,165,167],"thecocktail":[24],"party":[25,150],"effect.":[26],"For":[27],"decades,":[28],"researchers":[29],"focused":[31],"on":[32,173],"approaching":[33],"the":[34,47,64,87,90,100,103,109,119,148,188,193],"listening":[35],"ability":[36],"of":[37,67,74,102,108,131,156,182],"humans.":[38],"One":[39],"critical":[40],"issue":[41],"handling":[43],"speakers":[45],"because":[46,141],"nontarget":[50],"speech":[51,65],"signals":[52],"share":[53],"similar":[54],"characteristics,":[55],"complicating":[56],"their":[57],"discrimination.":[58],"Target":[59],"speech/speaker":[60],"extraction":[61],"(TSE)":[62],"isolates":[63],"signal":[66,157],"from":[71,117],"mixture":[73],"several":[75],"speakers,":[76],"with":[77],"or":[78],"without":[79],"noises":[80],"reverberations,":[82],"using":[83],"clues":[84,93],"identify":[86],"mixture.":[91],"Such":[92],"might":[94],"be":[95,124],"spatial":[97],"clue":[98],"indicating":[99],"direction":[101],"speaker,":[105],"video":[107],"speaker\u2019s":[110,120],"lips,":[111],"prerecorded":[114],"enrollment":[115],"utterance":[116],"which":[118],"voice":[121],"characteristics":[122],"derived.":[125],"TSE":[126],"an":[128,179],"emerging":[129],"field":[130],"research":[132],"has":[134],"received":[135],"increased":[136],"attention":[137],"recent":[139,174],"years":[140],"it":[142],"offers":[143],"practical":[145],"approach":[146],"cocktail":[149],"problem":[151],"involves":[153],"such":[154],"aspects":[155],"processing":[158,164],"audio,":[160],"visual,":[161],"array":[163],"well":[166],"deep":[168],"learning.":[169],"article":[171],"focuses":[172],"neural-based":[175],"approaches":[176],"presents":[178],"in-depth":[180],"overview":[181],"TSE.":[183],"We":[184],"guide":[185],"readers":[186],"through":[187],"different":[189],"major":[190],"approaches,":[191],"emphasizing":[192],"similarities":[194],"among":[195],"frameworks":[196],"discussing":[198],"potential":[199],"future":[200],"directions.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":9}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}