{"id":"https://openalex.org/W3171278394","doi":"https://doi.org/10.1109/taslp.2021.3083405","title":"Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation","display_name":"Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speech Separation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3171278394","doi":"https://doi.org/10.1109/taslp.2021.3083405","mag":"3171278394","pmid":"https://pubmed.ncbi.nlm.nih.gov/34212067"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3083405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3083405","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8240467","any_repository_has_fulltext":true},"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/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]},{"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":true,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210-1277 USA, while performing this work. He is now with Mitsubishi Electric Research Laboratories, Cambridge, MA 02139, USA","Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210-1277 USA, while performing this work. He is now with Mitsubishi Electric Research Laboratories, Cambridge, MA 02139, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"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":"Peidong Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210-1277 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210-1277 USA","institution_ids":["https://openalex.org/I52357470"]},{"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":["Department of Computer Science and Engineering & the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210-1277 USA","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering & the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210-1277 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering and the 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":3,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":["https://openalex.org/I4210159266","https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":10.772,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":{"value":0.99000067,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"2001","last_page":"2014"},"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":0.9976999759674072,"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/microphone","display_name":"Microphone","score":0.7880922555923462},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.7569723129272461},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6780694723129272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6558011174201965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6211329698562622},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.5340344905853271},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5247233510017395},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4618678689002991},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4546610713005066},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41949862241744995},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3953017592430115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28049686551094055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21048325300216675},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08936882019042969},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08773458003997803},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07075947523117065},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.06847083568572998}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7880922555923462},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.7569723129272461},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6780694723129272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6558011174201965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6211329698562622},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.5340344905853271},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5247233510017395},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4618678689002991},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4546610713005066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41949862241744995},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3953017592430115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28049686551094055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21048325300216675},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08936882019042969},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08773458003997803},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07075947523117065},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.06847083568572998},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2021.3083405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3083405","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"},{"id":"pmid:34212067","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34212067","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8240467","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8240467","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8240467","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8240467","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2289480995","https://openalex.org/W2291877678","https://openalex.org/W2398972335","https://openalex.org/W2516001803","https://openalex.org/W2552071709","https://openalex.org/W2559809918","https://openalex.org/W2568308529","https://openalex.org/W2734774145","https://openalex.org/W2792764867","https://openalex.org/W2803322398","https://openalex.org/W2885219692","https://openalex.org/W2892163332","https://openalex.org/W2897977894","https://openalex.org/W2900893004","https://openalex.org/W2938386503","https://openalex.org/W2945191446","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963317762","https://openalex.org/W2963446712","https://openalex.org/W2963452667","https://openalex.org/W2964058413","https://openalex.org/W2972460025","https://openalex.org/W2982456909","https://openalex.org/W3004309045","https://openalex.org/W3007256793","https://openalex.org/W3008880747","https://openalex.org/W3009032512","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015679215","https://openalex.org/W3015788098","https://openalex.org/W3015843733","https://openalex.org/W3016094953","https://openalex.org/W3016232124","https://openalex.org/W3016257794","https://openalex.org/W3028504434","https://openalex.org/W3032514799","https://openalex.org/W3032969657","https://openalex.org/W3086154751","https://openalex.org/W3099177480","https://openalex.org/W3099330747","https://openalex.org/W3151596526","https://openalex.org/W3162341667","https://openalex.org/W3163842642","https://openalex.org/W4289665794","https://openalex.org/W6639824700","https://openalex.org/W6749825310","https://openalex.org/W6751512325","https://openalex.org/W6769802879","https://openalex.org/W6774639334","https://openalex.org/W6778035800","https://openalex.org/W6781921439","https://openalex.org/W6782142667"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W201299990","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188"],"abstract_inverted_index":{"We":[0,23,85],"propose":[1],"multi-microphone":[2,88],"complex":[3,89],"spectral":[4,90],"mapping,":[5],"a":[6,49,75,128,135,142],"simple":[7],"way":[8],"of":[9,71,82,131],"applying":[10],"deep":[11,59],"learning":[12],"for":[13,17,112],"time-varying":[14],"non-linear":[15],"beamforming,":[16],"speaker":[18,27,37,110],"separation":[19,28,38,46,150],"in":[20,134],"reverberant":[21],"conditions.":[22],"aim":[24],"at":[25,74],"both":[26],"and":[29,39,55,67,99,105,160],"dereverberation.":[30],"Our":[31],"study":[32],"first":[33],"investigates":[34],"offline":[35],"utterance-wise":[36],"then":[40,86],"extends":[41],"to":[42,63,101,141],"block-online":[43,113],"continuous":[44],"speech":[45,73],"(CSS).":[47],"Assuming":[48],"fixed":[50,129],"array":[51,144],"geometry":[52],"between":[53],"training":[54],"testing,":[56],"we":[57],"train":[58],"neural":[60],"networks":[61],"(DNN)":[62],"predict":[64],"the":[65,79,146,155,161],"real":[66,143],"imaginary":[68],"(RI)":[69],"components":[70,81],"target":[72],"reference":[76],"microphone":[77],"from":[78],"RI":[80],"multiple":[83],"microphones.":[84],"integrate":[87],"mapping":[91],"with":[92,108,145],"minimum":[93],"variance":[94],"distortionless":[95],"response":[96],"(MVDR)":[97],"beamforming":[98],"post-filtering":[100],"further":[102],"improve":[103],"separation,":[104],"combine":[106],"it":[107,138],"frame-level":[109],"counting":[111],"CSS.":[114],"Although":[115],"our":[116],"system":[117],"is":[118,152],"trained":[119],"on":[120,127,154],"simulated":[121,156],"room":[122],"impulse":[123],"responses":[124],"(RIR)":[125],"based":[126],"number":[130],"microphones":[132],"arranged":[133],"given":[136],"geometry,":[137],"generalizes":[139],"well":[140],"same":[147],"geometry.":[148],"State-of-the-art":[149],"performance":[151],"obtained":[153],"two-talker":[157],"SMS-WSJ":[158],"corpus":[159],"real-recorded":[162],"LibriCSS":[163],"dataset.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":11}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}