{"id":"https://openalex.org/W3015372568","doi":"https://doi.org/10.1109/icassp40776.2020.9054177","title":"End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation","display_name":"End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015372568","doi":"https://doi.org/10.1109/icassp40776.2020.9054177","mag":"3015372568"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108961732","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0007-3882-3810"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048439332"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":16.8884,"has_fulltext":false,"cited_by_count":181,"citation_normalized_percentile":{"value":0.99537399,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6394","last_page":"6398"},"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":0.9976000189781189,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.6878638863563538},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6701112985610962},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6119700074195862},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.599170446395874},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5554660558700562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5416122078895569},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4771672785282135},{"id":"https://openalex.org/keywords/mutual-fund-separation-theorem","display_name":"Mutual fund separation theorem","score":0.47390425205230713},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.4293403625488281},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42134183645248413},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4202157258987427},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.41262006759643555},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.27750399708747864},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19918623566627502},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18641072511672974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.109243243932724},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10657703876495361},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09274318814277649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6878638863563538},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6701112985610962},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6119700074195862},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.599170446395874},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5554660558700562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5416122078895569},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4771672785282135},{"id":"https://openalex.org/C160471959","wikidata":"https://www.wikidata.org/wiki/Q17082552","display_name":"Mutual fund separation theorem","level":3,"score":0.47390425205230713},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4293403625488281},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42134183645248413},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4202157258987427},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.41262006759643555},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.27750399708747864},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19918623566627502},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18641072511672974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.109243243932724},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10657703876495361},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09274318814277649},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2117678320","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2577993889","https://openalex.org/W2589857635","https://openalex.org/W2636483419","https://openalex.org/W2714487941","https://openalex.org/W2718052359","https://openalex.org/W2734774145","https://openalex.org/W2753798143","https://openalex.org/W2767071179","https://openalex.org/W2891997645","https://openalex.org/W2897133973","https://openalex.org/W2898268964","https://openalex.org/W2952218014","https://openalex.org/W2962711740","https://openalex.org/W2963177459","https://openalex.org/W2963719584","https://openalex.org/W2963907629","https://openalex.org/W2964058413","https://openalex.org/W3004309045","https://openalex.org/W3015199127","https://openalex.org/W3099330747","https://openalex.org/W3104196160","https://openalex.org/W6738893770","https://openalex.org/W6744580074","https://openalex.org/W6754929296","https://openalex.org/W6755615850","https://openalex.org/W6768815455"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2396048001","https://openalex.org/W4240587264","https://openalex.org/W2348931051","https://openalex.org/W2011788874","https://openalex.org/W2109356272"],"abstract_inverted_index":{"An":[0],"important":[1],"problem":[2,162],"in":[3,127,159],"ad-hoc":[4,133],"microphone":[5],"speech":[6,98,165],"separation":[7,120,130,144],"is":[8],"how":[9,115],"to":[10,19,31,34,50,53],"guarantee":[11],"the":[12,20,29,38,41,45,48,102,119,143,153,156,160],"robustness":[13],"of":[14,24,37,125,155,163],"a":[15,87,106],"system":[16,30,49],"with":[17,40,56,132,146],"respect":[18],"locations":[21],"and":[22,94],"numbers":[23,124],"microphones.":[25],"The":[26],"former":[27],"requires":[28,47],"be":[32,51],"invariant":[33,96],"different":[35],"indexing":[36],"microphones":[39,126],"same":[42],"locations,":[43],"while":[44,68],"latter":[46],"able":[52],"process":[54],"inputs":[55],"varying":[57],"dimensions.":[58],"Conventional":[59],"optimization-based":[60],"beamforming":[61,111],"techniques":[62],"satisfy":[63],"these":[64],"requirements":[65],"by":[66],"definition,":[67],"for":[69,91],"deep":[70],"learning-based":[71],"end-to-end":[72,109],"systems":[73],"those":[74],"constraints":[75],"are":[76],"not":[77],"fully":[78],"addressed.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83,113,136],"propose":[84],"transform-average-concatenate":[85],"(TAC),":[86],"simple":[88],"design":[89],"paradigm":[90,158],"channel":[92],"permutation":[93],"number":[95],"multi-channel":[97],"separation.":[99,166],"Based":[100],"on":[101],"filter-and-sum":[103],"network":[104],"(FaSNet),":[105],"recently":[107],"proposed":[108,157],"time-domain":[110],"system,":[112],"show":[114,137],"TAC":[116,139],"significantly":[117,141],"improves":[118,142],"performance":[121,145],"across":[122],"various":[123],"noisy":[128],"reverberant":[129],"tasks":[131],"arrays.":[134],"Moreover,":[135],"that":[138],"also":[140],"fixed":[147],"geometry":[148],"array":[149],"configuration,":[150],"further":[151],"proving":[152],"effectiveness":[154],"general":[161],"multi-microphone":[164]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":17}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
