{"id":"https://openalex.org/W2891004713","doi":"https://doi.org/10.1109/icassp.2018.8462407","title":"DNN-Based Concurrent Speakers Detector and its Application to Speaker Extraction with LCMV Beamforming","display_name":"DNN-Based Concurrent Speakers Detector and its Application to Speaker Extraction with LCMV Beamforming","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891004713","doi":"https://doi.org/10.1109/icassp.2018.8462407","mag":"2891004713"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/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-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","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-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","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-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan 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":1.6514,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85254923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6712","last_page":"6716"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.7787827253341675},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6909473538398743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6825209856033325},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5428746342658997},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.509138286113739},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46210867166519165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42799875140190125},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4218965172767639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38544267416000366},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2625086307525635},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13519424200057983},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07214227318763733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787827253341675},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6909473538398743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6825209856033325},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5428746342658997},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.509138286113739},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46210867166519165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42799875140190125},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4218965172767639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38544267416000366},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2625086307525635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13519424200057983},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07214227318763733}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2005733316","https://openalex.org/W2042860487","https://openalex.org/W2060108923","https://openalex.org/W2061074721","https://openalex.org/W2101169486","https://openalex.org/W2141998673","https://openalex.org/W2147665979","https://openalex.org/W2155638623","https://openalex.org/W2236045036","https://openalex.org/W2289480995","https://openalex.org/W2517616541","https://openalex.org/W2568308529","https://openalex.org/W2594647430","https://openalex.org/W2702006285","https://openalex.org/W2767071179","https://openalex.org/W2767170918","https://openalex.org/W6675111666"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466","https://openalex.org/W2757081366"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,68,83,87,110,156],"new":[6],"control":[7],"mechanism":[8],"for":[9,102,117,135,150],"LCMV":[10,15,144],"beamforming.":[11],"Application":[12],"of":[13,24,43,46,51,121,159],"the":[14,29,38,52,76,104,119,122,140,143,152],"beamformer":[16,145],"to":[17,55,74],"speaker":[18,57,112,130,154],"separation":[19],"tasks":[20],"requires":[21],"accurate":[22,49],"estimates":[23],"its":[25],"building":[26],"blocks,":[27,142],"e.g.":[28],"noise":[30,105],"spatial":[31,106],"cross-power":[32],"spectral":[33],"density":[34],"(cPSD)":[35],"matrix":[36],"and":[37,125,148],"relative":[39],"transfer":[40],"function":[41],"(RTF)":[42],"all":[44,96],"sources":[45],"interest.":[47],"An":[48],"classification":[50],"input":[53],"frames":[54,91],"various":[56],"activity":[58],"patterns":[59],"can":[60],"facilitate":[61],"such":[62],"an":[63],"estimation":[64,136],"procedure.":[65],"We":[66],"propose":[67],"DNN-based":[69],"concurrent":[70],"speakers":[71,97],"detector":[72],"(CSD)":[73],"classify":[75],"noisy":[77,90,157],"frames.":[78],"The":[79],"CSD,":[80],"trained":[81],"in":[82],"supervised":[84],"manner":[85],"using":[86,139],"DNN,":[88],"classifies":[89],"into":[92],"three":[93],"classes:":[94],"1)":[95],"are":[98],"inactive":[99],"-":[100,115,133],"used":[101,116],"estimating":[103,118],"cPSD":[107],"matrix;":[108],"2)":[109],"single":[111],"is":[113,131,146],"active":[114,123,132],"RTF":[120],"speaker;":[124],"3)":[126],"more":[127],"than":[128],"one":[129],"discarded":[134],"purposes.":[137],"Finally,":[138],"estimated":[141],"constructed":[147],"applied":[149],"extracting":[151],"desired":[153],"from":[155],"mixture":[158],"speakers.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
