{"id":"https://openalex.org/W3132049316","doi":"https://doi.org/10.1109/icassp39728.2021.9413955","title":"Multi-Channel Speech Enhancement Using Graph Neural Networks","display_name":"Multi-Channel Speech Enhancement Using Graph Neural Networks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3132049316","doi":"https://doi.org/10.1109/icassp39728.2021.9413955","mag":"3132049316"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.06934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045277971","display_name":"Panagiotis Tzirakis","orcid":"https://orcid.org/0000-0001-9449-5339"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panagiotis Tzirakis","raw_affiliation_strings":["Facebook Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Facebook Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055065049","display_name":"Jacob Donley","orcid":"https://orcid.org/0000-0002-8401-798X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Donley","raw_affiliation_strings":["Facebook Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3415","last_page":"3419"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9959999918937683,"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/speech-enhancement","display_name":"Speech enhancement","score":0.63578200340271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6338092088699341},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6269018650054932},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6089315414428711},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5239691138267517},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5231310725212097},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4803522825241089},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4595467448234558},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44587424397468567},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.4320664405822754},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3429694175720215},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34155869483947754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3079603314399719},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2341693639755249},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2174648940563202},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17036354541778564},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10910391807556152},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.10017693042755127},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0899198055267334},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08210045099258423}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.63578200340271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6338092088699341},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6269018650054932},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6089315414428711},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5239691138267517},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5231310725212097},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4803522825241089},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4595467448234558},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44587424397468567},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.4320664405822754},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3429694175720215},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34155869483947754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3079603314399719},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2341693639755249},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2174648940563202},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17036354541778564},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10910391807556152},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.10017693042755127},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0899198055267334},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08210045099258423},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.06934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06934","pdf_url":"https://arxiv.org/pdf/2102.06934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2102.06934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.06934","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17023/bm6t-6b60","is_oa":true,"landing_page_url":"https://doi.org/10.17023/bm6t-6b60","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"},{"id":"mag:3132049316","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.06934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06934","pdf_url":"https://arxiv.org/pdf/2102.06934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132049316.pdf","grobid_xml":"https://content.openalex.org/works/W3132049316.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W176813254","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1991139021","https://openalex.org/W2091746061","https://openalex.org/W2098882755","https://openalex.org/W2127851351","https://openalex.org/W2136504847","https://openalex.org/W2141998673","https://openalex.org/W2408744528","https://openalex.org/W2519887557","https://openalex.org/W2558748708","https://openalex.org/W2568308529","https://openalex.org/W2589857635","https://openalex.org/W2593116425","https://openalex.org/W2610961739","https://openalex.org/W2889411318","https://openalex.org/W2889442120","https://openalex.org/W2890553422","https://openalex.org/W2907492528","https://openalex.org/W2937525188","https://openalex.org/W2945191446","https://openalex.org/W2948042249","https://openalex.org/W2962866211","https://openalex.org/W2963858333","https://openalex.org/W2963881378","https://openalex.org/W2964121744","https://openalex.org/W3013868095","https://openalex.org/W3015791598","https://openalex.org/W4210257598","https://openalex.org/W4255216832","https://openalex.org/W6631190155","https://openalex.org/W6680140577","https://openalex.org/W6684472137","https://openalex.org/W6726873649","https://openalex.org/W6734260513","https://openalex.org/W6775527634"],"related_works":["https://openalex.org/W3163591408","https://openalex.org/W3211258672","https://openalex.org/W3032905635","https://openalex.org/W3160138872","https://openalex.org/W3162816930","https://openalex.org/W3167503527","https://openalex.org/W2963435994","https://openalex.org/W3183676212","https://openalex.org/W3094427032","https://openalex.org/W3111290840","https://openalex.org/W3202551306","https://openalex.org/W3118399996","https://openalex.org/W2500440664","https://openalex.org/W3177021849","https://openalex.org/W3091660421","https://openalex.org/W3165958588","https://openalex.org/W3165495321","https://openalex.org/W3117235369","https://openalex.org/W2951466457","https://openalex.org/W3201292656"],"abstract_inverted_index":{"Multi-channel":[0],"speech":[1,7],"enhancement":[2],"aims":[3],"to":[4,73,79,114,137],"extract":[5],"clean":[6],"from":[8,15],"a":[9,48,58,62,67,102],"noisy":[10],"mixture":[11],"using":[12,120],"signals":[13],"captured":[14],"multiple":[16],"microphones.":[17,127],"Recently":[18],"proposed":[19],"methods":[20],"tackle":[21],"this":[22,44],"problem":[23],"by":[24,52,94],"incorporating":[25,95],"deep":[26],"neural":[27,76],"network":[28],"models":[29],"with":[30,117],"spatial":[31,81],"filtering":[32],"techniques":[33],"such":[34],"as":[35,57],"the":[36,84,98,130],"minimum":[37],"variance":[38],"distortionless":[39],"response":[40],"(MVDR)":[41],"beamformer.":[42],"In":[43],"paper,":[45],"we":[46],"introduce":[47],"different":[49,85,121],"research":[50],"direction":[51],"viewing":[53],"each":[54],"audio":[55],"channel":[56],"node":[59],"lying":[60],"in":[61,97],"non-Euclidean":[63],"space":[64,100],"and,":[65],"specifically,":[66],"graph.":[68],"This":[69],"formulation":[70],"allows":[71],"us":[72],"apply":[74],"graph":[75,90],"networks":[77,92],"(GNN)":[78],"find":[80],"correlations":[82],"among":[83],"channels":[86],"(nodes).":[87],"We":[88,105],"utilize":[89],"convolution":[91],"(GCN)":[93],"them":[96],"embedding":[99],"of":[101,126,132],"U-Net":[103],"architecture.":[104],"use":[106],"LibriSpeech":[107],"dataset":[108],"and":[109,124],"simulate":[110],"room":[111],"acoustics":[112],"data":[113],"extensively":[115],"experiment":[116],"our":[118,133],"approach":[119,134],"array":[122],"types,":[123],"number":[125],"Results":[128],"indicate":[129],"superiority":[131],"when":[135],"compared":[136],"prior":[138],"state-of-the-art":[139],"method.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}