{"id":"https://openalex.org/W3207728800","doi":"https://doi.org/10.1109/icassp43922.2022.9747395","title":"One Model to Enhance Them All: Array Geometry Agnostic Multi-Channel Personalized Speech Enhancement","display_name":"One Model to Enhance Them All: Array Geometry Agnostic Multi-Channel Personalized Speech Enhancement","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207728800","doi":"https://doi.org/10.1109/icassp43922.2022.9747395","mag":"3207728800"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747395","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073861062","display_name":"Hassan Taherian","orcid":"https://orcid.org/0000-0002-7548-3081"},"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"]},{"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":"Hassan Taherian","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA","The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088950","display_name":"\u015eefik Emre Eskimez","orcid":"https://orcid.org/0000-0001-6259-5925"},"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":"Sefik Emre Eskimez","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","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","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101528069","display_name":"Huaming Wang","orcid":"https://orcid.org/0000-0002-4434-7482"},"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":"Huaming Wang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"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","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103158343","display_name":"Xuedong Huang","orcid":"https://orcid.org/0000-0003-4550-7908"},"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":"Xuedong Huang","raw_affiliation_strings":["Microsoft,Redmond,WA,USA","Microsoft, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"271","last_page":"275"},"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":0.9944000244140625,"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":0.9932000041007996,"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":0.7449690103530884},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7410123348236084},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6482430100440979},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6071981191635132},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6024382710456848},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5926702618598938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5165373682975769},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4416986405849457},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4137660562992096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29832684993743896},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1442640721797943},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10274985432624817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449690103530884},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7410123348236084},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6482430100440979},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6071981191635132},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6024382710456848},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5926702618598938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5165373682975769},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4416986405849457},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4137660562992096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29832684993743896},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1442640721797943},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10274985432624817},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/icassp43922.2022.9747395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747395","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W1569447338","https://openalex.org/W2291877678","https://openalex.org/W2593116425","https://openalex.org/W2770119437","https://openalex.org/W2889411318","https://openalex.org/W2906042495","https://openalex.org/W2945191446","https://openalex.org/W2949756029","https://openalex.org/W2970911383","https://openalex.org/W2973062255","https://openalex.org/W2973179291","https://openalex.org/W2987307811","https://openalex.org/W3000358149","https://openalex.org/W3015372568","https://openalex.org/W3015636705","https://openalex.org/W3015791598","https://openalex.org/W3094893851","https://openalex.org/W3096408984","https://openalex.org/W3120907516","https://openalex.org/W3142516134","https://openalex.org/W3167217740","https://openalex.org/W3171278394","https://openalex.org/W3194338569","https://openalex.org/W3196660995","https://openalex.org/W3197042120","https://openalex.org/W3198100319","https://openalex.org/W3198543387","https://openalex.org/W3198667862","https://openalex.org/W3206706278","https://openalex.org/W4206633762","https://openalex.org/W6633847657","https://openalex.org/W6734260513","https://openalex.org/W6746278845","https://openalex.org/W6755462816","https://openalex.org/W6757632829"],"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/W2109356272","https://openalex.org/W2132495960"],"abstract_inverted_index":{"With":[0],"the":[1,40,60,82,116,122,143,146],"recent":[2],"surge":[3],"of":[4,85,145],"video":[5],"conferencing":[6],"tools":[7],"usage,":[8],"providing":[9],"high-quality":[10,105],"speech":[11,31,42,56,133,137],"signals":[12],"and":[13,27,88,135],"accurate":[14],"captions":[15],"have":[16],"become":[17],"essential":[18],"to":[19,50,53,59,74],"conduct":[20],"day-to-day":[21],"business":[22],"or":[23],"connect":[24],"with":[25,39],"friends":[26],"families.":[28],"Single-channel":[29],"personalized":[30],"enhancement":[32,43],"(PSE)":[33],"methods":[34,45],"show":[35,114],"promising":[36],"results":[37,113],"compared":[38],"unconditional":[41],"(SE)":[44],"in":[46,57,131],"these":[47],"scenarios":[48],"due":[49],"their":[51],"ability":[52],"remove":[54],"interfering":[55],"addition":[58],"environmental":[61],"noise.":[62],"In":[63],"this":[64],"work,":[65],"we":[66,92],"leverage":[67],"spatial":[68,89],"information":[69],"afforded":[70],"by":[71],"microphone":[72,110,128],"arrays":[73],"improve":[75],"such":[76],"systems\u2019":[77],"performance":[78],"further.":[79],"We":[80,140],"investigate":[81],"relative":[83],"importance":[84],"speaker":[86],"embeddings":[87],"features.":[90],"Moreover,":[91],"propose":[93],"a":[94,104,126],"new":[95],"causal":[96],"array-geometry-agnostic":[97],"multi-channel":[98],"PSE":[99],"model,":[100],"which":[101],"can":[102],"generate":[103],"enhanced":[106],"signal":[107],"from":[108],"arbitrary":[109],"geometry.":[111],"Experimental":[112],"that":[115],"proposed":[117,147],"geometry":[118,130],"agnostic":[119],"model":[120,123],"outperforms":[121],"trained":[124],"on":[125],"specific":[127],"array":[129,151],"both":[132],"quality":[134],"automatic":[136],"recognition":[138],"accuracy.":[139],"also":[141],"demonstrate":[142],"effectiveness":[144],"approach":[148],"for":[149],"unseen":[150],"geometries.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}