{"id":"https://openalex.org/W3093265230","doi":"https://doi.org/10.1109/icassp39728.2021.9414265","title":"Self-Attention Generative Adversarial Network for Speech Enhancement","display_name":"Self-Attention Generative Adversarial Network for Speech Enhancement","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3093265230","doi":"https://doi.org/10.1109/icassp39728.2021.9414265","mag":"3093265230"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414265","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/2010.09132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Queen Mary University of London, UK","Queen Mary, University of London (UK)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Queen Mary, University of London (UK)","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102936404","display_name":"Huy L. Nguy\u00ean","orcid":"https://orcid.org/0000-0001-5128-6545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huy Le Nguyen","raw_affiliation_strings":["HCMC University of Technology, Vietnam","HCMC University of Technology,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HCMC University of Technology, Vietnam","institution_ids":[]},{"raw_affiliation_string":"HCMC University of Technology,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074236126","display_name":"Oliver Y. Ch\u00e9n","orcid":"https://orcid.org/0000-0002-5696-3127"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Y. Chen","raw_affiliation_strings":["University of Oxford, UK","Univ. of Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Univ. of Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044840858","display_name":"Philipp Koch","orcid":"https://orcid.org/0000-0002-8795-758X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Koch","raw_affiliation_strings":["University of L\u00fcbeck, Germany","#N##TAB##TAB##TAB##TAB# University of L\u00fcbeck, Germany#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# University of L\u00fcbeck, Germany#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041584595","display_name":"Ngoc Q. K. Duong","orcid":"https://orcid.org/0000-0002-7627-8194"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngoc Q. K. Duong","raw_affiliation_strings":["InterDigital R&D France, France","InterDigital R&D France (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"InterDigital R&D France, France","institution_ids":[]},{"raw_affiliation_string":"InterDigital R&D France (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["Singapore Institute of Technology, Singapore","Singapore Institute of Technology , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]},{"raw_affiliation_string":"Singapore Institute of Technology , Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063948113","display_name":"Alfred Mertins","orcid":"https://orcid.org/0000-0001-5718-577X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alfred Mertins","raw_affiliation_strings":["University of L\u00fcbeck, Germany","#N##TAB##TAB##TAB##TAB# University of L\u00fcbeck, Germany#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# University of L\u00fcbeck, Germany#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I9341345"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9058,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72737322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7103","last_page":"7107"},"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":0.9887999892234802,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9871000051498413,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7494535446166992},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.659428060054779},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5967907309532166},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5747048258781433},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5675127506256104},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5625304579734802},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.48172762989997864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4655616581439972},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43871310353279114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4097989499568939},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38927578926086426},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.05360770225524902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494535446166992},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.659428060054779},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5967907309532166},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5747048258781433},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5675127506256104},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5625304579734802},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.48172762989997864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4655616581439972},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43871310353279114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4097989499568939},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38927578926086426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.05360770225524902},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414265","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414265","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:2010.09132","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.09132","pdf_url":"https://arxiv.org/pdf/2010.09132","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3093265230","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.09132","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:figshare.com:article/24217425","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Self-attention_generative_adversarial_network_for_speech_enhancement/24217425","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":null,"raw_type":"Conference contribution"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/74442","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74442","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"pmh:oai:serval.unil.ch:BIB_39D4B5BC3EB9","is_oa":false,"landing_page_url":"https://serval.unil.ch/notice/serval:BIB_39D4B5BC3EB9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401797","display_name":"SERVAL (Universit\u00e9 de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210093590","host_organization_name":"Swiss School of Archaeology in Greece","host_organization_lineage":["https://openalex.org/I4210093590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7103-7107","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2010.09132","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.09132","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/d4ph-sx28","is_oa":true,"landing_page_url":"https://doi.org/10.17023/d4ph-sx28","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.09132","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.09132","pdf_url":"https://arxiv.org/pdf/2010.09132","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W1983108229","https://openalex.org/W2042407743","https://openalex.org/W2044893557","https://openalex.org/W2051428568","https://openalex.org/W2094721231","https://openalex.org/W2099471712","https://openalex.org/W2121077055","https://openalex.org/W2121973264","https://openalex.org/W2141998673","https://openalex.org/W2271840356","https://openalex.org/W2593414223","https://openalex.org/W2603567530","https://openalex.org/W2791210709","https://openalex.org/W2804078698","https://openalex.org/W2939497224","https://openalex.org/W2940177920","https://openalex.org/W2943493972","https://openalex.org/W2963091558","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963373786","https://openalex.org/W2963453742","https://openalex.org/W2963684088","https://openalex.org/W2963836885","https://openalex.org/W2964089206","https://openalex.org/W2972451902","https://openalex.org/W2976556660","https://openalex.org/W2998832642","https://openalex.org/W3096008106","https://openalex.org/W3097945073","https://openalex.org/W3102190437","https://openalex.org/W6663678776","https://openalex.org/W6685352114","https://openalex.org/W6694517276","https://openalex.org/W6718379498","https://openalex.org/W6748582592","https://openalex.org/W6752378368"],"related_works":["https://openalex.org/W3161273075","https://openalex.org/W3182112704","https://openalex.org/W3020389402","https://openalex.org/W3006410914","https://openalex.org/W3162188526","https://openalex.org/W3204097565","https://openalex.org/W3091719055","https://openalex.org/W2922197700","https://openalex.org/W2515863432","https://openalex.org/W3193934472","https://openalex.org/W2997713487","https://openalex.org/W3007057000","https://openalex.org/W3127041580","https://openalex.org/W2439078092","https://openalex.org/W3157913045","https://openalex.org/W2593303827","https://openalex.org/W2789131247","https://openalex.org/W3100174574","https://openalex.org/W2172010943","https://openalex.org/W3175122022"],"abstract_inverted_index":{"Existing":[0],"generative":[1],"adversarial":[2],"networks":[3],"(GANs)":[4],"for":[5],"speech":[6,45],"enhancement":[7,46,100],"solely":[8],"rely":[9],"on":[10],"the":[11,20,38,57,61,65,95,121,126],"convolution":[12],"operation,":[13],"which":[14],"may":[15],"obscure":[16],"temporal":[17],"dependencies":[18],"across":[19,94],"sequence":[21],"input.":[22,52],"To":[23],"remedy":[24],"this":[25],"issue,":[26],"we":[27,54],"propose":[28],"a":[29,44],"self-attention":[30,62,87],"layer":[31,63,70,124],"adapted":[32],"from":[33],"non-local":[34],"attention,":[35],"coupled":[36],"with":[37,68,125],"convolutional":[39],"and":[40],"deconvolutional":[41],"layers":[42,67,107],"of":[43,59,77,99],"GAN":[47],"(SEGAN)":[48],"using":[49],"raw":[50],"signal":[51],"Further,":[53],"empirically":[55],"study":[56],"effect":[58],"placing":[60],"at":[64,75,104,120],"(de)convolutional":[66,106,123],"varying":[69],"indices":[71],"as":[72,74],"well":[73],"all":[76],"them":[78],"when":[79],"memory":[80,128],"allows.":[81],"Our":[82],"experiments":[83],"show":[84],"that":[85,114],"introducing":[86],"to":[88,91],"SEGAN":[89],"leads":[90],"consistent":[92],"improvement":[93],"objective":[96],"evaluation":[97],"metrics":[98],"performance.":[101],"Furthermore,":[102],"applying":[103],"different":[105],"does":[108],"not":[109],"significantly":[110],"alter":[111],"performance,":[112],"suggesting":[113],"it":[115],"can":[116],"be":[117],"conveniently":[118],"applied":[119],"highest-level":[122],"smallest":[127],"overhead1.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}