{"id":"https://openalex.org/W4390692126","doi":"https://doi.org/10.1109/taslp.2024.3352259","title":"A Novel Approach to Multi-Channel Speech Enhancement Based on Graph Neural Networks","display_name":"A Novel Approach to Multi-Channel Speech Enhancement Based on Graph Neural Networks","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390692126","doi":"https://doi.org/10.1109/taslp.2024.3352259"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3352259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3352259","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/A5046577116","display_name":"Ngoc Chau Hoang","orcid":"https://orcid.org/0009-0004-3278-779X"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Hoang Ngoc Chau","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0004-3278-779X","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016362901","display_name":"Tien-Dat Bui","orcid":"https://orcid.org/0009-0004-7571-7230"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien Dat Bui","raw_affiliation_strings":["Viettel Cyberspace Center, Viettel Group, Vietnam"],"raw_orcid":"https://orcid.org/0009-0004-7571-7230","affiliations":[{"raw_affiliation_string":"Viettel Cyberspace Center, Viettel Group, Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101708713","display_name":"Huu Nguyen","orcid":"https://orcid.org/0009-0005-3655-9644"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Huu Binh Nguyen","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0009-0005-3655-9644","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217635","display_name":"Thanh Thi Duong","orcid":"https://orcid.org/0000-0001-5854-5845"},"institutions":[{"id":"https://openalex.org/I29199639","display_name":"Hanoi University of Mining and Geology","ror":"https://ror.org/01rw3qm79","country_code":"VN","type":"education","lineage":["https://openalex.org/I29199639"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thanh Thi Hien Duong","raw_affiliation_strings":["Hanoi University of Mining and Geology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0001-5854-5845","affiliations":[{"raw_affiliation_string":"Hanoi University of Mining and Geology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I29199639"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101764507","display_name":"Quoc Cuong Nguyen","orcid":"https://orcid.org/0000-0002-5641-5040"},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Quoc Cuong Nguyen","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-5362-2968","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Hanoi University of Science and Technology, Hanoi, Vietnam","institution_ids":["https://openalex.org/I94518387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046577116"],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":4.6035,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95281769,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"1133","last_page":"1144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965999722480774,"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":0.9908000230789185,"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/computer-science","display_name":"Computer science","score":0.7805663347244263},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6281464099884033},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5773534178733826},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5632972717285156},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5170996189117432},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49286460876464844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4898347556591034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4643217921257019},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45079731941223145},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4498525857925415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3991319537162781},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.332849383354187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805663347244263},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6281464099884033},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5773534178733826},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5632972717285156},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5170996189117432},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49286460876464844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4898347556591034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4643217921257019},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45079731941223145},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4498525857925415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3991319537162781},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.332849383354187},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3352259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3352259","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W2060108923","https://openalex.org/W2069681747","https://openalex.org/W2141998673","https://openalex.org/W2168729028","https://openalex.org/W2219249508","https://openalex.org/W2398042854","https://openalex.org/W2402526332","https://openalex.org/W2516001803","https://openalex.org/W2517616541","https://openalex.org/W2558460151","https://openalex.org/W2558748708","https://openalex.org/W2568308529","https://openalex.org/W2593116425","https://openalex.org/W2609317876","https://openalex.org/W2809418595","https://openalex.org/W2889442120","https://openalex.org/W2890489755","https://openalex.org/W2900893004","https://openalex.org/W2907492528","https://openalex.org/W2945191446","https://openalex.org/W2948042249","https://openalex.org/W2963084622","https://openalex.org/W2963242190","https://openalex.org/W2964051675","https://openalex.org/W2964058413","https://openalex.org/W2972802573","https://openalex.org/W2979750740","https://openalex.org/W2990045899","https://openalex.org/W3004309045","https://openalex.org/W3009032512","https://openalex.org/W3015372568","https://openalex.org/W3015791598","https://openalex.org/W3016257794","https://openalex.org/W3020724926","https://openalex.org/W3152893301","https://openalex.org/W3162188526","https://openalex.org/W3162341667","https://openalex.org/W3163591408","https://openalex.org/W3171278394","https://openalex.org/W3192281612","https://openalex.org/W3196940724","https://openalex.org/W3198511309","https://openalex.org/W3198533616","https://openalex.org/W4210402803","https://openalex.org/W4214498238","https://openalex.org/W4221164004","https://openalex.org/W4224917453","https://openalex.org/W4224931298","https://openalex.org/W4226071457","https://openalex.org/W4247128071","https://openalex.org/W4255216832","https://openalex.org/W4312219134","https://openalex.org/W4312982325","https://openalex.org/W4385245566","https://openalex.org/W6688816777","https://openalex.org/W6720006811","https://openalex.org/W6726873649","https://openalex.org/W6736685754","https://openalex.org/W6757817989","https://openalex.org/W6802810016","https://openalex.org/W6848935878"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W3013693939","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W4402568167","https://openalex.org/W3131327266","https://openalex.org/W2734887215"],"abstract_inverted_index":{"Multi-channel":[0],"speech":[1,165],"enhancement":[2,166],"aims":[3],"at":[4],"utilizing":[5],"spatial":[6,84],"relationships":[7],"between":[8],"signals":[9,69],"captured":[10],"from":[11],"a":[12,40,50,71,99,106,113,159],"microphone":[13,127],"array":[14],"along":[15],"with":[16,124],"temporal-spectral":[17,89],"information":[18,90],"efficiently":[19],"to":[20,29,43,82,111,129,143],"estimate":[21],"the":[22,64,75,125,135],"clean":[23],"target.":[24],"An":[25],"emerging":[26],"approach":[27,139],"is":[28,121,158],"design":[30],"deep":[31,174],"learning-based":[32,175],"end-to-end":[33,52],"architectures.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"provide":[39],"new":[41],"way":[42],"process":[44],"latent":[45],"multi-channel":[46,68],"representations.":[47],"We":[48,133],"introduce":[49],"novel":[51,160],"system":[53],"called":[54],"<italic":[55],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[56],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">temporal":[57],"graph":[58,72,78,95],"convolutional":[59,96,108],"network</i>":[60],",":[61],"which":[62],"views":[63],"embedding":[65],"space":[66],"of":[67,77,137],"as":[70,86,88],"and":[73,153,177],"leverages":[74],"power":[76],"neural":[79],"networks":[80,97],"(GNNs)":[81],"analyze":[83],"correlations":[85],"well":[87],"simultaneously.":[91],"To":[92],"be":[93],"specific,":[94],"(GCNs),":[98],"popular":[100],"GNN":[101],"variant,":[102],"are":[103],"integrated":[104],"into":[105],"complex":[107,114],"encoder-decoder":[109],"structure":[110],"compute":[112],"ideal":[115],"ratio":[116],"mask.":[117],"The":[118],"estimated":[119],"mask":[120],"subsequently":[122],"multiplied":[123],"reference":[126],"spectrogram":[128],"get":[130],"enhanced":[131],"speech.":[132],"demonstrate":[134],"superiority":[136],"our":[138],"by":[140],"comparing":[141],"it":[142],"state-of-the-art":[144],"methods":[145],"on":[146],"ConferencingSpeech":[147],"2021":[148],"Challenge":[149],"data.":[150],"Our":[151],"results":[152],"analyses":[154],"prove":[155],"that":[156],"GCN":[157],"yet":[161],"promising":[162],"mechanism":[163],"for":[164,172,179],"systems,":[167],"providing":[168],"an":[169],"interesting":[170],"alternative":[171],"recent":[173],"approaches":[176],"inspiration":[178],"future":[180],"research.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}