{"id":"https://openalex.org/W3161590371","doi":"https://doi.org/10.1109/icassp39728.2021.9414998","title":"Speaker Activity Driven Neural Speech Extraction","display_name":"Speaker Activity Driven Neural Speech Extraction","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161590371","doi":"https://doi.org/10.1109/icassp39728.2021.9414998","mag":"3161590371"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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 Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, 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, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Czechia","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 Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, 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 Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, 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 Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, 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":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6099","last_page":"6103"},"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":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8091301918029785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7945226430892944},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7621762752532959},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5848003625869751},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5745884776115417},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5725334882736206},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49182748794555664},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.48920106887817383},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4659631550312042},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44715049862861633},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4427466094493866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41010528802871704}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8091301918029785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945226430892944},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7621762752532959},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5848003625869751},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5745884776115417},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5725334882736206},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49182748794555664},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.48920106887817383},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4659631550312042},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44715049862861633},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4427466094493866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41010528802871704},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/icassp39728.2021.9414998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2078639319","https://openalex.org/W2127851351","https://openalex.org/W2145700204","https://openalex.org/W2164637175","https://openalex.org/W2169896329","https://openalex.org/W2514740276","https://openalex.org/W2638067502","https://openalex.org/W2702006285","https://openalex.org/W2734774145","https://openalex.org/W2749510669","https://openalex.org/W2766352194","https://openalex.org/W2787692317","https://openalex.org/W2882979035","https://openalex.org/W2892365986","https://openalex.org/W2900212944","https://openalex.org/W2939771864","https://openalex.org/W2951130829","https://openalex.org/W2962780374","https://openalex.org/W2964171275","https://openalex.org/W2964238697","https://openalex.org/W2972802573","https://openalex.org/W3010196324","https://openalex.org/W3015636705","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3024085360","https://openalex.org/W3025260599","https://openalex.org/W3057611960","https://openalex.org/W3094831814","https://openalex.org/W4289665794","https://openalex.org/W6678799340","https://openalex.org/W6684878041","https://openalex.org/W6754743415","https://openalex.org/W6773721078","https://openalex.org/W6774558098","https://openalex.org/W6784900337"],"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/W4280634406"],"abstract_inverted_index":{"Target":[0],"speech":[1,6,60,68],"extraction,":[2],"which":[3,127],"extracts":[4],"the":[5,38,46,86,93,96,104],"of":[7,37,48,95,145],"a":[8,12,64,110,139],"target":[9,39],"speaker":[10,16,49,65,105],"in":[11,129,134],"mixture":[13],"given":[14],"auxiliary":[15,54],"clues,":[17],"has":[18],"recently":[19],"received":[20],"increased":[21],"interest.":[22],"Various":[23],"clues":[24],"have":[25],"been":[26],"investigated":[27],"such":[28],"as":[29,52],"pre-recorded":[30],"enrollment":[31],"utterances,":[32],"direction":[33],"information,":[34],"or":[35],"video":[36],"speaker.":[40],"In":[41],"this":[42,116],"paper,":[43],"we":[44],"explore":[45],"use":[47],"activity":[50,66,106],"information":[51],"an":[53],"clue":[55],"for":[56,88,99],"single-channel":[57],"neural":[58,70],"network-based":[59],"extraction.":[61],"We":[62,90,113],"propose":[63],"driven":[67],"extraction":[69],"network":[71],"(ADEnet)":[72],"and":[73],"show":[74,114],"that":[75,115],"it":[76],"can":[77,121],"achieve":[78],"performance":[79],"levels":[80],"competitive":[81],"with":[82,138],"enrollment-based":[83],"approaches,":[84],"without":[85],"need":[87],"pre-recordings.":[89],"further":[91],"demonstrate":[92],"potential":[94],"proposed":[97],"approach":[98,120],"processing":[100],"meeting-like":[101],"recordings,":[102],"where":[103],"is":[107],"obtained":[108],"from":[109],"diarization":[111],"system.":[112],"simple":[117],"yet":[118],"practical":[119],"successfully":[122],"extract":[123],"speakers":[124],"after":[125],"diarization,":[126],"results":[128],"improved":[130],"ASR":[131],"performance,":[132],"especially":[133],"high":[135],"overlapping":[136],"conditions,":[137],"relative":[140],"word":[141],"error":[142],"rate":[143],"reduction":[144],"up":[146],"to":[147],"25%.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}