{"id":"https://openalex.org/W3026111682","doi":"https://doi.org/10.1109/taslp.2020.2995273","title":"Monaural Speech Dereverberation Using Temporal Convolutional Networks With Self Attention","display_name":"Monaural Speech Dereverberation Using Temporal Convolutional Networks With Self Attention","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3026111682","doi":"https://doi.org/10.1109/taslp.2020.2995273","mag":"3026111682","pmid":"https://pubmed.ncbi.nlm.nih.gov/33748325"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2995273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2995273","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971181","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076372893","display_name":"Yan Zhao","orcid":"https://orcid.org/0000-0001-8595-3297"},"institutions":[{"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":"Yan Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8595-3297","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"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":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"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"]},{"id":"https://openalex.org/I4210137835","display_name":"Starkey Hearing Technologies (United States)","ror":"https://ror.org/02yhzgr66","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137835"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Starkey Hearing Technologies, Eden Prairie, MN, USA","Facebook Reality Labs, Facebook, Inc., Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0002-3027-7567","affiliations":[{"raw_affiliation_string":"Starkey Hearing Technologies, Eden Prairie, MN, USA","institution_ids":["https://openalex.org/I4210137835"]},{"raw_affiliation_string":"Facebook Reality Labs, Facebook, Inc., Redmond, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100375823","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0002-6272-4069"},"institutions":[{"id":"https://openalex.org/I4210137835","display_name":"Starkey Hearing Technologies (United States)","ror":"https://ror.org/02yhzgr66","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137835"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Starkey Hearing Technologies, Eden Prairie, MN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Starkey Hearing Technologies, Eden Prairie, MN, USA","institution_ids":["https://openalex.org/I4210137835"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8203,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":{"value":0.98695539,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"1598","last_page":"1607"},"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":0.9983000159263611,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.996999979019165,"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/reverberation","display_name":"Reverberation","score":0.878523588180542},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7517164945602417},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7237297296524048},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7076894640922546},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.6940490007400513},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.5617699027061462},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5510424375534058},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.5037686228752136},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4473169445991516},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4439725875854492},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41286301612854004},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3396179974079132},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.28743934631347656},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24156558513641357},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15488365292549133},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10876008868217468},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08077678084373474},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0694088339805603}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.878523588180542},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7517164945602417},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7237297296524048},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7076894640922546},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.6940490007400513},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.5617699027061462},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5510424375534058},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.5037686228752136},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4473169445991516},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4439725875854492},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41286301612854004},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3396179974079132},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.28743934631347656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24156558513641357},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15488365292549133},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10876008868217468},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08077678084373474},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0694088339805603},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2020.2995273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2995273","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"},{"id":"pmid:33748325","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33748325","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"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":null},{"id":"pmh:oai:pubmedcentral.nih.gov:7971181","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971181","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7971181","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971181","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320306842","display_name":"Starkey Hearing Foundation","ror":"https://ror.org/02yhzgr66"},{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1591801644","https://openalex.org/W1677182931","https://openalex.org/W1973669708","https://openalex.org/W1998648683","https://openalex.org/W2006129368","https://openalex.org/W2024490156","https://openalex.org/W2062355771","https://openalex.org/W2063669828","https://openalex.org/W2110322414","https://openalex.org/W2117678320","https://openalex.org/W2120847449","https://openalex.org/W2125114513","https://openalex.org/W2125930537","https://openalex.org/W2130722890","https://openalex.org/W2136682440","https://openalex.org/W2144786298","https://openalex.org/W2147166770","https://openalex.org/W2156387975","https://openalex.org/W2164502538","https://openalex.org/W2188162373","https://openalex.org/W2194775991","https://openalex.org/W2233657726","https://openalex.org/W2242685705","https://openalex.org/W2302255633","https://openalex.org/W2327501763","https://openalex.org/W2531409750","https://openalex.org/W2542605056","https://openalex.org/W2592939477","https://openalex.org/W2612445135","https://openalex.org/W2613904329","https://openalex.org/W2736786568","https://openalex.org/W2743945814","https://openalex.org/W2792764867","https://openalex.org/W2798405286","https://openalex.org/W2890401420","https://openalex.org/W2896457183","https://openalex.org/W2899771611","https://openalex.org/W2906724656","https://openalex.org/W2935934262","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962832181","https://openalex.org/W2962866211","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963840672","https://openalex.org/W2964089206","https://openalex.org/W2964121744","https://openalex.org/W2964189376","https://openalex.org/W2964265128","https://openalex.org/W2972542211","https://openalex.org/W3099330747","https://openalex.org/W4297775537","https://openalex.org/W4299838440","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6635446068","https://openalex.org/W6656414902","https://openalex.org/W6678818196","https://openalex.org/W6682889407","https://openalex.org/W6686978693","https://openalex.org/W6696085341","https://openalex.org/W6737664043","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6741240231","https://openalex.org/W6742632731","https://openalex.org/W6749825310","https://openalex.org/W6755207826","https://openalex.org/W6756040250","https://openalex.org/W6757200458"],"related_works":["https://openalex.org/W2732511158","https://openalex.org/W2621851636","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661"],"abstract_inverted_index":{"In":[0,126],"daily":[1],"listening":[2],"environments,":[3],"human":[4],"speech":[5,24,48,117],"is":[6],"often":[7],"degraded":[8],"by":[9],"room":[10,135,138],"reverberation,":[11,42],"especially":[12],"under":[13],"highly":[14],"reverberant":[15,124],"conditions.":[16,125],"Such":[17],"degradation":[18],"poses":[19],"a":[20,45,63,73,79,93,120],"challenge":[21],"for":[22],"many":[23],"processing":[25],"systems,":[26],"where":[27],"the":[28,39,59,86,100,110],"performance":[29],"becomes":[30],"much":[31],"worse":[32],"than":[33],"in":[34,119],"anechoic":[35,90],"environments.":[36],"To":[37],"combat":[38],"effect":[40],"of":[41,89,116,123],"we":[43],"propose":[44],"monaural":[46],"(single-channel)":[47],"dereverberation":[49],"algorithm":[50,112],"using":[51],"temporal":[52,74],"convolutional":[53,75],"networks":[54],"with":[55],"self":[56],"attention.":[57],"Specifically,":[58],"proposed":[60,111],"system":[61],"includes":[62],"self-attention":[64],"module":[65,97],"to":[66,77,85,98,131],"produce":[67],"dynamic":[68],"representations":[69,84],"given":[70],"input":[71],"features,":[72],"network":[76],"learn":[78],"nonlinear":[80],"mapping":[81],"from":[82],"such":[83],"magnitude":[87,102],"spectrum":[88],"speech,":[91,144],"and":[92,145],"one-dimensional":[94],"(1-D)":[95],"convolution":[96],"smooth":[99],"enhanced":[101],"among":[103],"adjacent":[104],"frames.":[105],"Systematic":[106],"evaluations":[107],"demonstrate":[108],"that":[109],"improves":[113],"objective":[114],"metrics":[115],"quality":[118],"wide":[121],"range":[122],"addition,":[127],"it":[128],"generalizes":[129],"well":[130],"untrained":[132],"reverberation":[133],"times,":[134],"sizes,":[136],"measured":[137],"impulse":[139],"responses,":[140],"real-world":[141],"recorded":[142],"noisy-reverberant":[143],"different":[146],"speakers.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}