{"id":"https://openalex.org/W2900893004","doi":"https://doi.org/10.1109/taslp.2018.2881912","title":"Combining Spectral and Spatial Features for Deep Learning Based Blind Speaker Separation","display_name":"Combining Spectral and Spatial Features for Deep Learning Based Blind Speaker Separation","publication_year":2018,"publication_date":"2018-11-20","ids":{"openalex":"https://openalex.org/W2900893004","doi":"https://doi.org/10.1109/taslp.2018.2881912","mag":"2900893004"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2881912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2881912","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-4204-9430","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":11.3176,"has_fulltext":false,"cited_by_count":147,"citation_normalized_percentile":{"value":0.98986577,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"27","issue":"2","first_page":"457","last_page":"468"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9968000054359436,"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":0.9957000017166138,"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/beamforming","display_name":"Beamforming","score":0.6414626836776733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6374465227127075},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6170052289962769},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6040787100791931},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5763566493988037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5022592544555664},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.44786304235458374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4395086467266083},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3452167212963104},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.33764296770095825},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1518058180809021},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11212211847305298}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6414626836776733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6374465227127075},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6170052289962769},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6040787100791931},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5763566493988037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5022592544555664},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.44786304235458374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4395086467266083},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3452167212963104},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33764296770095825},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1518058180809021},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11212211847305298},{"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/taslp.2018.2881912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2881912","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G4666743193","display_name":null,"funder_award_id":"FA8750-15-1-0279","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"},{"id":"https://openalex.org/G8888347223","display_name":null,"funder_award_id":"IIS-1409431","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321449","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1544785557","https://openalex.org/W1982172017","https://openalex.org/W1992879732","https://openalex.org/W1996304098","https://openalex.org/W2018735295","https://openalex.org/W2031583051","https://openalex.org/W2068071321","https://openalex.org/W2129116669","https://openalex.org/W2129171989","https://openalex.org/W2131470542","https://openalex.org/W2143027228","https://openalex.org/W2166458192","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2289480995","https://openalex.org/W2304609584","https://openalex.org/W2460742184","https://openalex.org/W2465050681","https://openalex.org/W2516001803","https://openalex.org/W2559260703","https://openalex.org/W2561557072","https://openalex.org/W2568308529","https://openalex.org/W2575498233","https://openalex.org/W2586584460","https://openalex.org/W2599685671","https://openalex.org/W2698117193","https://openalex.org/W2718052359","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2750380122","https://openalex.org/W2750446090","https://openalex.org/W2766794899","https://openalex.org/W2781711557","https://openalex.org/W2792498316","https://openalex.org/W2793272123","https://openalex.org/W2794289187","https://openalex.org/W2799119527","https://openalex.org/W2803322398","https://openalex.org/W2803583024","https://openalex.org/W2804228164","https://openalex.org/W2889411318","https://openalex.org/W2890489755","https://openalex.org/W2891219041","https://openalex.org/W2891405874","https://openalex.org/W2891984996","https://openalex.org/W2891997645","https://openalex.org/W2892163332","https://openalex.org/W2917831833","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2963301902","https://openalex.org/W2964275228","https://openalex.org/W3124972797","https://openalex.org/W6679489070","https://openalex.org/W6743406453","https://openalex.org/W6743465039","https://openalex.org/W6747544821","https://openalex.org/W6748559479","https://openalex.org/W6750842128","https://openalex.org/W6754577425"],"related_works":["https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W2206035908","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W1493012537","https://openalex.org/W1977167953","https://openalex.org/W2769861442","https://openalex.org/W2162158162","https://openalex.org/W1980506188"],"abstract_inverted_index":{"This":[0],"study":[1],"tightly":[2,150],"integrates":[3,132],"complementary":[4],"spectral":[5,40,53,58,133],"and":[6,50,57,77,98,122,131,134,159],"spatial":[7,36,56],"features":[8,41,59],"for":[9,102],"deep":[10,120],"learning":[11],"based":[12,147,180],"multi-channel":[13],"speaker":[14,45,86,97,109,173,178],"separation":[15,165],"in":[16,62,152,188],"reverberant":[17,171,177],"environments.":[18],"The":[19,55,105],"key":[20],"idea":[21],"is":[22,111,149],"to":[23,42,72],"localize":[24],"individual":[25],"speakers":[26],"so":[27],"that":[28,66,96],"an":[29,47],"enhancement":[30],"network":[31],"can":[32],"be":[33],"trained":[34,68],"on":[35,170,181],"as":[37,39],"well":[38],"extract":[43],"the":[44,67,73,82,85,127,139,153,157],"from":[46],"estimated":[48],"direction":[49,83,103],"with":[51],"specific":[52],"structures.":[54],"are":[60,70],"designed":[61],"a":[63,114,182],"way":[64],"such":[65],"models":[69],"blind":[71],"number":[74,184],"of":[75,84,87,185],"microphones":[76,186],"microphone":[78],"geometry.":[79,191],"To":[80],"determine":[81],"interest,":[88],"we":[89],"identify":[90],"time-frequency":[91],"(T-F)":[92],"units":[93],"dominated":[94],"by":[95,113,155,162],"only":[99],"use":[100],"them":[101],"estimation.":[104],"T-F":[106,145],"unit":[107],"level":[108],"dominance":[110],"determined":[112],"two-channel":[115],"chimera++":[116],"network,":[117],"which":[118,175],"combines":[119],"clustering":[121],"permutation":[123],"invariant":[124],"training":[125],"at":[126,138],"objective":[128],"function":[129],"level,":[130],"interchannel":[135],"phase":[136],"patterns":[137],"input":[140],"feature":[141],"level.":[142],"In":[143],"addition,":[144],"masking":[146],"beamforming":[148],"integrated":[151],"system":[154],"leveraging":[156],"magnitudes":[158],"phases":[160],"produced":[161],"beamforming.":[163],"Strong":[164],"performance":[166],"has":[167],"been":[168],"observed":[169],"talker-independent":[172],"separation,":[174],"separates":[176],"mixtures":[179],"random":[183],"arranged":[187],"arbitrary":[189],"linear-array":[190]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}