{"id":"https://openalex.org/W3015636705","doi":"https://doi.org/10.1109/icassp40776.2020.9054683","title":"Improving Speaker Discrimination of Target Speech Extraction With Time-Domain Speakerbeam","display_name":"Improving Speaker Discrimination of Target Speech Extraction With Time-Domain Speakerbeam","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015636705","doi":"https://doi.org/10.1109/icassp40776.2020.9054683","mag":"3015636705"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/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":true,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"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/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"],"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":["Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czechia"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT and IT4I Center of Excellence, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"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"],"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/A5073111123","display_name":"Naohiro Tawara","orcid":null},"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":"Naohiro Tawara","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"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/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"],"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/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"],"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":7,"corresponding_author_ids":["https://openalex.org/A5023868166"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":11.5166,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.99124424,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"691","last_page":"695"},"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":0.9997000098228455,"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":0.9993000030517578,"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":0.809201717376709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8029837608337402},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.630521833896637},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5788995027542114},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5510415434837341},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5018126964569092},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.48558229207992554},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.46507999300956726},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42752882838249207},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4266315996646881},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4124095141887665},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4103376269340515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37786951661109924},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3494427800178528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.809201717376709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8029837608337402},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.630521833896637},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5788995027542114},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5510415434837341},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5018126964569092},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.48558229207992554},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.46507999300956726},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42752882838249207},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4266315996646881},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4124095141887665},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4103376269340515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37786951661109924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3494427800178528},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W1544785557","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2398776621","https://openalex.org/W2558649592","https://openalex.org/W2587150483","https://openalex.org/W2734774145","https://openalex.org/W2749510669","https://openalex.org/W2801839390","https://openalex.org/W2882979035","https://openalex.org/W2889418727","https://openalex.org/W2891054259","https://openalex.org/W2892163332","https://openalex.org/W2892365986","https://openalex.org/W2924115626","https://openalex.org/W2935846637","https://openalex.org/W2939771864","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2964238697","https://openalex.org/W2972693890","https://openalex.org/W2973062255","https://openalex.org/W2973179291","https://openalex.org/W3010925296","https://openalex.org/W3015788098","https://openalex.org/W3099330747","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6601563604","https://openalex.org/W6678799340","https://openalex.org/W6688843265","https://openalex.org/W6754743415"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Target":[0],"speech":[1,52,62,68,78,148,192,206],"extraction,":[2],"which":[3,27,142],"extracts":[4],"a":[5,10,47,58,70,126,136],"single":[6],"target":[7,16,34,71,103,205],"source":[8],"in":[9,93,202],"mixture":[11],"given":[12],"clues":[13],"about":[14],"the":[15,33,102,106,117,154],"speaker,":[17],"has":[18,143],"attracted":[19],"increasing":[20],"attention.":[21],"We":[22,184],"have":[23,87],"recently":[24],"proposed":[25,134],"SpeakerBeam,":[26],"exploits":[28],"an":[29,171],"adaptation":[30],"utterance":[31],"of":[32,53,69,121,129,156,204],"speaker":[35,72,104,118,173],"to":[36,45,61,100,132,159,178],"extract":[37],"his/her":[38],"voice":[39,89,182],"characteristics":[40],"that":[41,54,133,187],"are":[42,167],"then":[43],"used":[44],"guide":[46],"neural":[48],"network":[49,140],"towards":[50],"extracting":[51],"speaker.":[55],"SpeakerBeam":[56,130],"presents":[57],"practical":[59],"alternative":[60],"separation":[63,139],"as":[64,92],"it":[65,82,97],"enables":[66],"tracking":[67],"across":[73],"utterances,":[74],"and":[75,199],"achieves":[76],"promising":[77],"extraction":[79,193],"performance.":[80],"However,":[81],"sometimes":[83],"fails":[84],"when":[85,163],"speakers":[86,162],"similar":[88,131],"characteristics,":[90],"such":[91],"same-gender":[94,197],"mixtures,":[95,198],"because":[96],"is":[98],"difficult":[99],"discriminate":[101,161],"from":[105],"interfering":[107],"speakers.":[108],"In":[109],"this":[110],"paper,":[111],"we":[112,124,151],"investigate":[113,152],"strategies":[114,189],"for":[115,135,147,176,196],"improving":[116],"discrimination":[119],"capability":[120],"SpeakerBeam.":[122],"First,":[123],"propose":[125],"time-domain":[127,137],"implementation":[128],"audio":[138],"(TasNet),":[141],"achieved":[144],"state-of-the-art":[145],"performance":[146],"separation.":[149],"Besides,":[150],"(1)":[153],"use":[155],"spatial":[157],"features":[158],"better":[160],"microphone":[164],"array":[165],"recordings":[166],"available,":[168],"(2)":[169],"adding":[170],"auxiliary":[172],"identification":[174],"loss":[175],"helping":[177],"learn":[179],"more":[180],"discriminative":[181],"characteristics.":[183],"show":[185],"experimentally":[186],"these":[188],"greatly":[190],"improve":[191],"performance,":[194],"especially":[195],"outperform":[200],"TasNet":[201],"terms":[203],"extraction.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":13}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}