{"id":"https://openalex.org/W2939771864","doi":"https://doi.org/10.1109/icassp.2019.8683087","title":"Compact Network for Speakerbeam Target Speaker Extraction","display_name":"Compact Network for Speakerbeam Target Speaker Extraction","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939771864","doi":"https://doi.org/10.1109/icassp.2019.8683087","mag":"2939771864"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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 and IT4I Center of Excellence, Brno University of Technology, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT and IT4I Center of Excellence, Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"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, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication 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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"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":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6965","last_page":"6969"},"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":0.7641069293022156},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7091177105903625},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5868625640869141},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.55443274974823},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4908807873725891},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4474918842315674},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4168045222759247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37234294414520264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36874905228614807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641069293022156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7091177105903625},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5868625640869141},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.55443274974823},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4908807873725891},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4474918842315674},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4168045222759247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37234294414520264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36874905228614807},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/icassp.2019.8683087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W1522301498","https://openalex.org/W2079623482","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2144763279","https://openalex.org/W2150769028","https://openalex.org/W2221409856","https://openalex.org/W2398776621","https://openalex.org/W2407685581","https://openalex.org/W2460742184","https://openalex.org/W2514740276","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2749510669","https://openalex.org/W2787692317","https://openalex.org/W2791636785","https://openalex.org/W2801839390","https://openalex.org/W2891833136","https://openalex.org/W2962788625","https://openalex.org/W2962866211","https://openalex.org/W2964121744","https://openalex.org/W2964238697","https://openalex.org/W2973062255","https://openalex.org/W6601563604","https://openalex.org/W6631190155","https://openalex.org/W6678799340","https://openalex.org/W6688843265","https://openalex.org/W6714030504","https://openalex.org/W6743590492","https://openalex.org/W6755462816","https://openalex.org/W6798498067"],"related_works":["https://openalex.org/W4307784074","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2499802997","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"Speech":[0],"separation":[1,228],"that":[2,80,96,214,223],"separates":[3],"a":[4,21,48,53,67,76,103,134,150,186,225,231],"mixture":[5],"of":[6,11,32,44,47,52,57,95,109,137,149,153,172,189,206,218,224],"speech":[7,46,77,129,155,215,227],"signals":[8],"into":[9],"each":[10],"its":[12],"sources":[13],"has":[14,25],"been":[15],"an":[16,92],"active":[17],"research":[18],"topic":[19],"for":[20,127,208],"long":[22],"time":[23],"and":[24,197,200],"seen":[26],"recent":[27],"progress":[28],"with":[29,102,158,222,230],"the":[30,84,119,147,154,162,170,204],"advent":[31],"deep":[33],"learning.":[34],"A":[35],"related":[36],"problem":[37],"is":[38,66,81,125],"target":[39,49,70,85,128],"speaker":[40,50,71,86],"extraction,":[41,130],"i.e.":[42],"extraction":[43,72,78,156,216],"only":[45],"out":[51],"mixture,":[54],"given":[55],"characteristics":[56],"his/her":[58],"voice.":[59],"We":[60,191],"have":[61],"recently":[62],"proposed":[63],"SpeakerBeam,":[64],"which":[65,107],"neural":[68],"network-based":[69],"method.":[73],"Speaker-Beam":[74],"uses":[75],"network":[79,157,233],"adapted":[82],"to":[83,144,177],"using":[87],"auxiliary":[88,120,163],"features":[89],"derived":[90,117,160],"from":[91,118,161],"adaptation":[93,105],"utterance":[94],"speaker.":[97],"Initially,":[98],"we":[99,142,212],"implemented":[100],"SpeakerBeam":[101,207,219],"factorized":[104,123],"layer,":[106],"consists":[108],"several":[110],"parallel":[111],"linear":[112],"transformations":[113],"weighted":[114],"by":[115,175],"weights":[116,159],"features.":[121,164],"The":[122],"layer":[124,152],"effective":[126],"but":[131],"it":[132,180],"requires":[133],"large":[135],"number":[136,171],"parameters.":[138],"In":[139],"this":[140],"paper,":[141],"propose":[143],"simply":[145],"scale":[146],"activations":[148],"hidden":[151],"This":[165],"simpler":[166],"approach":[167,194],"greatly":[168],"reduces":[169],"model":[173],"parameters":[174],"up":[176],"60%,":[178],"making":[179],"much":[181],"more":[182],"practical,":[183],"while":[184],"maintaining":[185],"similar":[187,232],"level":[188],"performance.":[190],"tested":[192],"our":[193],"on":[195],"simulated":[196],"real":[198],"noisy":[199],"reverberant":[201],"mixtures,":[202],"showing":[203],"potential":[205],"real-life":[209],"applications.":[210],"Moreover,":[211],"showed":[213],"performance":[217],"compares":[220],"favorably":[221],"state-of-the-art":[226],"method":[229],"configuration.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}