{"id":"https://openalex.org/W2900130877","doi":"https://doi.org/10.1109/iwaenc.2018.8521259","title":"Attention-Based Neural Network for Joint Diarization and Speaker Extraction","display_name":"Attention-Based Neural Network for Joint Diarization and Speaker Extraction","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2900130877","doi":"https://doi.org/10.1109/iwaenc.2018.8521259","mag":"2900130877"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5080213609","display_name":"Shlomo E. Chazan","orcid":"https://orcid.org/0000-0002-6614-6112"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Shlomo E. Chazan","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilang University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilang University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001052072","display_name":"Sharon Gannot","orcid":"https://orcid.org/0000-0002-2885-170X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sharon Gannot","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilang University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilang University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005409420","display_name":"Jacob Goldberger","orcid":"https://orcid.org/0000-0002-2225-1914"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jacob Goldberger","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilang University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilang University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080213609"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":0.9948,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77640479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"301","last_page":"305"},"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":0.9994999766349792,"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":0.9980000257492065,"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":0.829392671585083},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7098551988601685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6642957925796509},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5734012722969055},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5171120166778564},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5120899677276611},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5106368660926819},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5028268694877625},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4847145080566406},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4594815969467163},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4584803581237793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.421896755695343},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3846263587474823},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3706760108470917},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07258692383766174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829392671585083},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7098551988601685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6642957925796509},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5734012722969055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5171120166778564},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5120899677276611},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5106368660926819},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5028268694877625},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4847145080566406},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4594815969467163},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4584803581237793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.421896755695343},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3846263587474823},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3706760108470917},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07258692383766174},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc.2018.8521259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W285277413","https://openalex.org/W1514535095","https://openalex.org/W2005733316","https://openalex.org/W2042860487","https://openalex.org/W2061074721","https://openalex.org/W2101169486","https://openalex.org/W2133564696","https://openalex.org/W2147665979","https://openalex.org/W2155638623","https://openalex.org/W2221409856","https://openalex.org/W2289480995","https://openalex.org/W2398042854","https://openalex.org/W2402583539","https://openalex.org/W2517616541","https://openalex.org/W2568308529","https://openalex.org/W2586584460","https://openalex.org/W2594647430","https://openalex.org/W2606300880","https://openalex.org/W2702006285","https://openalex.org/W2767071179","https://openalex.org/W2767170918","https://openalex.org/W2803322398","https://openalex.org/W2891004713","https://openalex.org/W2892163332","https://openalex.org/W2902796441","https://openalex.org/W2962715207","https://openalex.org/W2964308564","https://openalex.org/W6675111666","https://openalex.org/W6679434410","https://openalex.org/W6726313835","https://openalex.org/W6756430648"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1879255185","https://openalex.org/W1977167953","https://openalex.org/W2162158162","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W4247736853","https://openalex.org/W1980506188","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Multi-microphone,":[0],"DNN-based,":[1],"speech":[2],"enhancement":[3,14],"and":[4,70,92,123,143,146],"speaker":[5,90,101,153],"separation/extraction":[6],"algorithms":[7],"have":[8],"recently":[9],"gained":[10],"increasing":[11],"popularity.":[12],"The":[13],"capabilities":[15],"of":[16,137],"spatial":[17],"processor":[18],"can":[19,35,147],"be":[20,36],"very":[21,37],"high,":[22],"provided":[23],"that":[24,103],"all":[25],"its":[26],"building":[27],"blocks":[28],"are":[29],"accurately":[30],"estimated.":[31],"Data-driven":[32],"estimation":[33,79],"approaches":[34],"attractive":[38],"since":[39],"they":[40],"do":[41],"not":[42],"rely":[43],"on":[44],"accurate":[45],"statistical":[46],"models,":[47],"which":[48],"is":[49,59,104],"usually":[50],"unavailable.":[51],"However,":[52],"training":[53,142],"a":[54,60,83,120],"DNN":[55,99,122],"with":[56],"multi-microphone":[57],"data":[58],"challenging":[61],"task,":[62],"due":[63],"to":[64,106,150],"inevitable":[65],"differences":[66],"between":[67,141],"the":[68,107,112,128,135,139],"train":[69],"test":[71,144],"phases.":[72],"In":[73,111],"this":[74],"work,":[75],"we":[76],"present":[77],"an":[78,97,124,151],"procedure":[80],"for":[81,89,100],"controlling":[82],"linearly-constrained":[84],"minimum":[85],"variance":[86],"(LCMV)":[87],"beamformer":[88],"extraction":[91,154],"noise":[93],"reduction.":[94],"We":[95],"propose":[96],"attention-based":[98],"diarization":[102],"applicable":[105],"task":[108],"at":[109],"hand.":[110],"proposed":[113],"scheme,":[114],"each":[115],"microphone":[116],"signal":[117],"propagates":[118],"through":[119],"dedicated":[121],"attention":[125],"mechanism":[126],"selects":[127],"most":[129],"informative":[130],"microphone.":[131],"This":[132],"approach":[133],"has":[134],"potential":[136],"mitigating":[138],"mismatch":[140],"phases":[145],"therefore":[148],"lead":[149],"improved":[152],"performance.":[155]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-05T06:14:27.290980","created_date":"2025-10-10T00:00:00"}
