{"id":"https://openalex.org/W3134695619","doi":"https://doi.org/10.1109/taslp.2021.3064421","title":"Dense CNN With Self-Attention for Time-Domain Speech Enhancement","display_name":"Dense CNN With Self-Attention for Time-Domain Speech Enhancement","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3134695619","doi":"https://doi.org/10.1109/taslp.2021.3064421","mag":"3134695619","pmid":"https://pubmed.ncbi.nlm.nih.gov/33997107"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3064421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3064421","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/8118093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050492887","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3352-7453"},"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":true,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","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 43210 USA","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210 USA","institution_ids":["https://openalex.org/I52357470"]},{"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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050492887"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":21.8518,"has_fulltext":false,"cited_by_count":174,"citation_normalized_percentile":{"value":0.9979196,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"1270","last_page":"1279"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9911999702453613,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9886999726295471,"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":0.8010655641555786},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6894814372062683},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.549472987651825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5456593036651611},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5377882122993469},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5365476608276367},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49894165992736816},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.49415114521980286},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4583877623081207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3376792371273041},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2542056441307068},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0965823233127594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8010655641555786},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6894814372062683},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.549472987651825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5456593036651611},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5377882122993469},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5365476608276367},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49894165992736816},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.49415114521980286},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4583877623081207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3376792371273041},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2542056441307068},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0965823233127594},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2021.3064421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3064421","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:33997107","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33997107","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:8118093","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8118093","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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:8118093","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8118093","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G404307092","display_name":null,"funder_award_id":"R02DC015521","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G4332130492","display_name":null,"funder_award_id":"R01DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"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":68,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W2024490156","https://openalex.org/W2044893557","https://openalex.org/W2048142341","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2141998673","https://openalex.org/W2165899180","https://openalex.org/W2168379380","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2405774341","https://openalex.org/W2476548250","https://openalex.org/W2516342150","https://openalex.org/W2535388113","https://openalex.org/W2678916739","https://openalex.org/W2747161606","https://openalex.org/W2774389566","https://openalex.org/W2804078698","https://openalex.org/W2889286744","https://openalex.org/W2892009249","https://openalex.org/W2892356933","https://openalex.org/W2897371647","https://openalex.org/W2937484199","https://openalex.org/W2938901746","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963453742","https://openalex.org/W2964121744","https://openalex.org/W2970971581","https://openalex.org/W2991361823","https://openalex.org/W2998678989","https://openalex.org/W3012897083","https://openalex.org/W3015197852","https://openalex.org/W3015199127","https://openalex.org/W3015219411","https://openalex.org/W3016129867","https://openalex.org/W3026111682","https://openalex.org/W3049430014","https://openalex.org/W3094911989","https://openalex.org/W3099330747","https://openalex.org/W4253928870","https://openalex.org/W4295312788","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6639532686","https://openalex.org/W6713658392","https://openalex.org/W6726607834","https://openalex.org/W6728226663","https://openalex.org/W6729060410","https://openalex.org/W6735429107","https://openalex.org/W6739901393","https://openalex.org/W6743354777","https://openalex.org/W6752378368","https://openalex.org/W6766978945","https://openalex.org/W6775369996","https://openalex.org/W6775689321","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W2353602216","https://openalex.org/W4390516098","https://openalex.org/W2367078749","https://openalex.org/W2381798600","https://openalex.org/W1910583078","https://openalex.org/W2351618306","https://openalex.org/W2133117170","https://openalex.org/W2181948922"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,42],"in":[2,10,43,60,80],"the":[3,21,24,44,61,64,107,134,150,164],"time":[4,45],"domain":[5],"is":[6,48,137],"becoming":[7],"increasingly":[8],"popular":[9],"recent":[11],"years,":[12],"due":[13],"to":[14,17,172],"its":[15],"capability":[16],"jointly":[18],"enhance":[19],"both":[20,153],"magnitude":[22,109,154],"and":[23,51,63,70,76,92,128,155,174],"phase":[25],"of":[26,86,110,125],"speech.":[27,112],"In":[28],"this":[29],"work,":[30],"we":[31,97,117],"propose":[32,118],"a":[33,67,84,103,119,129,142],"dense":[34,68],"convolutional":[35],"network":[36,90],"(DCN)":[37],"with":[38,55,102,163],"self-attention":[39],"for":[40],"speech":[41,127,176],"domain.":[46],"DCN":[47,161],"an":[49,71],"encoder":[50,62],"decoder":[52,65],"based":[53,105,122,138],"architecture":[54],"skip":[56],"connections.":[57],"Each":[58],"layer":[59],"comprises":[66],"block":[69],"attention":[72,77],"module.":[73],"Dense":[74],"blocks":[75],"modules":[78],"help":[79],"feature":[81,87],"extraction":[82],"using":[83],"combination":[85],"reuse,":[88],"increased":[89],"depth,":[91],"maximum":[93],"context":[94],"aggregation.":[95],"Furthermore,":[96],"reveal":[98],"previously":[99],"unknown":[100],"problems":[101],"loss":[104,121,136,151,166],"on":[106,123,139],"spectral":[108],"enhanced":[111,126],"To":[113],"alleviate":[114],"these":[115],"problems,":[116],"novel":[120],"magnitudes":[124,140],"predicted":[130],"noise.":[131],"Even":[132],"though":[133],"proposed":[135,165],"only,":[141],"constraint":[143],"imposed":[144],"by":[145],"noise":[146],"prediction":[147],"ensures":[148],"that":[149,160],"enhances":[152],"phase.":[156],"Experimental":[157],"results":[158],"demonstrate":[159],"trained":[162],"substantially":[167],"outperforms":[168],"other":[169],"state-of-the-art":[170],"approaches":[171],"causal":[173],"non-causal":[175],"enhancement.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":45},{"year":2023,"cited_by_count":44},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":15}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
