{"id":"https://openalex.org/W2951130829","doi":"https://doi.org/10.1109/jstsp.2019.2922820","title":"SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures","display_name":"SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures","publication_year":2019,"publication_date":"2019-06-13","ids":{"openalex":"https://openalex.org/W2951130829","doi":"https://doi.org/10.1109/jstsp.2019.2922820","mag":"2951130829"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2019.2922820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2922820","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","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/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":"Katerina Zmolikova","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0003-4438-8580","affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"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 Communications Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5175-7834","affiliations":[{"raw_affiliation_string":"NTT Communications Science Laboratories, NTT Corporation, 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":[{"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":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communications Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communications Science Laboratories, NTT Corporation, 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 Communications Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communications Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"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":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communications Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7487-7150","affiliations":[{"raw_affiliation_string":"NTT Communications Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"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":"Lukas Burget","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","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 Cernocky","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Brno, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0002-8800-0210","affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.0343,"has_fulltext":false,"cited_by_count":251,"citation_normalized_percentile":{"value":0.99513279,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"13","issue":"4","first_page":"800","last_page":"814"},"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":0.9998999834060669,"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":0.9995999932289124,"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":0.8436366319656372},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.756689190864563},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7311550974845886},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6897602677345276},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6563587188720703},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5960986614227295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49644237756729126},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.480049729347229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46940934658050537},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4604106843471527},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45862382650375366},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4222240447998047},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37442028522491455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8436366319656372},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.756689190864563},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7311550974845886},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6897602677345276},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6563587188720703},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5960986614227295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49644237756729126},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.480049729347229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46940934658050537},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4604106843471527},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45862382650375366},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4222240447998047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37442028522491455},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2019.2922820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2922820","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315323","display_name":"Technology Agency of the Czech Republic","ror":null},{"id":"https://openalex.org/F4320322748","display_name":"Vysok\u00e9 U\u010den\u00ed Technick\u00e9 v Brn\u011b","ror":"https://ror.org/03613d656"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W285277413","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1571447047","https://openalex.org/W1982728343","https://openalex.org/W1985371235","https://openalex.org/W1989314204","https://openalex.org/W1989954041","https://openalex.org/W2044222806","https://openalex.org/W2069681747","https://openalex.org/W2070707809","https://openalex.org/W2079362249","https://openalex.org/W2079623482","https://openalex.org/W2087368178","https://openalex.org/W2094147890","https://openalex.org/W2115599677","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2135029798","https://openalex.org/W2146635662","https://openalex.org/W2147174722","https://openalex.org/W2150415460","https://openalex.org/W2150769028","https://openalex.org/W2158143227","https://openalex.org/W2164240571","https://openalex.org/W2187089797","https://openalex.org/W2221409856","https://openalex.org/W2289394825","https://openalex.org/W2304609584","https://openalex.org/W2345067732","https://openalex.org/W2398042854","https://openalex.org/W2398776621","https://openalex.org/W2407685581","https://openalex.org/W2460742184","https://openalex.org/W2513836842","https://openalex.org/W2514740276","https://openalex.org/W2517616541","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2699350432","https://openalex.org/W2734774145","https://openalex.org/W2749510669","https://openalex.org/W2749659773","https://openalex.org/W2787692317","https://openalex.org/W2791636785","https://openalex.org/W2794289187","https://openalex.org/W2801839390","https://openalex.org/W2887080793","https://openalex.org/W2891609809","https://openalex.org/W2891833136","https://openalex.org/W2892163332","https://openalex.org/W2939771864","https://openalex.org/W2962715207","https://openalex.org/W2962788625","https://openalex.org/W2962866211","https://openalex.org/W2964238697","https://openalex.org/W2973062255","https://openalex.org/W3143596294","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6680012447","https://openalex.org/W6681474505","https://openalex.org/W6714030504","https://openalex.org/W6743590492","https://openalex.org/W6755462816"],"related_works":["https://openalex.org/W2997340161","https://openalex.org/W1901037250","https://openalex.org/W2185667427","https://openalex.org/W3045817537","https://openalex.org/W146217425","https://openalex.org/W3086303851","https://openalex.org/W2401203293","https://openalex.org/W2045259680","https://openalex.org/W2162615272","https://openalex.org/W2157029620"],"abstract_inverted_index":{"The":[0,220],"processing":[1,231],"of":[2,11,38,124,213,216,225,235],"speech":[3,20,45,172],"corrupted":[4],"by":[5,100,164,204],"interfering":[6],"overlapping":[7,196],"speakers":[8,53,125],"is":[9],"one":[10,72],"the":[12,42,52,55,92,101,105,118,122,127,139,143,153,176,179,201,206,211,214,217,223,230,233,236],"challenging":[13],"problems":[14],"with":[15,190],"regards":[16],"to":[17,120,134,147,151,159],"today's":[18],"automatic":[19,171],"recognition":[21],"systems.":[22],"Recently,":[23],"approaches":[24,40],"based":[25,94],"on":[26,95,178],"deep":[27],"learning":[28],"have":[29],"made":[30],"great":[31],"progress":[32],"toward":[33],"solving":[34],"this":[35,79,149],"problem.":[36],"Most":[37],"these":[39,187],"tackle":[41],"problem":[43,106],"as":[44,61,107,114],"separation,":[46],"i.e.,":[47],"they":[48],"blindly":[49],"recover":[50],"all":[51],"from":[54,75,91,138],"mixture.":[56,77,128],"In":[57,78],"some":[58],"scenarios,":[59],"such":[60,113],"smart":[62],"personal":[63],"devices,":[64],"we":[65,81,131],"may":[66],"however":[67],"be":[68],"interested":[69],"in":[70,126,167,229],"recovering":[71],"target":[73,89,102,144],"speaker":[74,90,108,145,165,207,227],"a":[76,84,88,136],"paper,":[80],"introduce":[82],"SpeakerBeam,":[83,130],"method":[85],"for":[86,170],"extracting":[87],"mixture":[93],"an":[96],"adaptation":[97,140,166,218],"utterance":[98,141],"spoken":[99],"speaker.":[103,154],"Formulating":[104],"extraction":[109],"avoids":[110],"certain":[111],"issues":[112],"label":[115],"permutation":[116],"and":[117,146,183,186,209,232],"need":[119],"determine":[121],"number":[123],"With":[129],"jointly":[132],"learn":[133],"extract":[135,152],"representation":[137,150],"characterizing":[142],"use":[148],"We":[155,174,198],"explore":[156],"several":[157],"ways":[158],"do":[160],"this,":[161],"mostly":[162],"inspired":[163],"acoustic":[168],"models":[169],"recognition.":[173],"evaluate":[175],"performance":[177],"widely":[180],"used":[181],"WSJ0-2mix":[182],"WSJ0-3mix":[184],"datasets,":[185],"datasets":[188],"modified":[189],"more":[191,194],"noise":[192],"or":[193],"realistic":[195],"patterns.":[197],"further":[199],"analyze":[200],"learned":[202],"behavior":[203],"exploring":[205],"representations":[208],"assessing":[210],"effect":[212],"length":[215],"data.":[219],"results":[221],"show":[222],"benefit":[224],"including":[226],"information":[228],"effectiveness":[234],"proposed":[237],"method.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":34},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}