{"id":"https://openalex.org/W3015197852","doi":"https://doi.org/10.1109/icassp40776.2020.9054536","title":"Densely Connected Neural Network with Dilated Convolutions for Real-Time Speech Enhancement in The Time Domain","display_name":"Densely Connected Neural Network with Dilated Convolutions for Real-Time Speech Enhancement in The Time Domain","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015197852","doi":"https://doi.org/10.1109/icassp40776.2020.9054536","mag":"3015197852"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054536","doi":"https://doi.org/10.1109/icassp40776.2020.9054536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054536","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5050492887","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3352-7453","observed_orcids":["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":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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","observed_orcids":["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, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":12.1963,"has_fulltext":false,"cited_by_count":161,"citation_normalized_percentile":{"value":0.99097665,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6629","last_page":"6633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T11309","display_name":"Music and Audio Processing","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.9139999747276306},{"id":"https://openalex.org/keywords/real-time-speech-enhancement","display_name":"real-time speech enhancement","score":0.9330000281333923},{"id":"https://openalex.org/keywords/time-domain-speech-enhancement","display_name":"time-domain speech enhancement","score":0.8040000200271606},{"id":"https://openalex.org/keywords/dilated-convolution","display_name":"dilated convolution","score":0.8450000286102295},{"id":"https://openalex.org/keywords/causal-convolution","display_name":"causal convolution","score":0.996999979019165},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.8510000109672546},{"id":"https://openalex.org/keywords/skip-connections","display_name":"skip connections","score":0.9879999756813049},{"id":"https://openalex.org/keywords/frequency-domain-loss","display_name":"frequency domain loss","score":0.9779999852180481},{"id":"https://openalex.org/keywords/intelligibility","display_name":"intelligibility","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.8656167387962341},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8116649389266968},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.6801447868347168},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6554279923439026},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6086467504501343},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4674433469772339},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46619361639022827},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4180232286453247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38191789388656616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38113364577293396},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35812899470329285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.336304247379303},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2010720670223236},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11736932396888733},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10131528973579407},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/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/icassp40776.2020.9054536","doi":"https://doi.org/10.1109/icassp40776.2020.9054536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054536","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.4099999964237213,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W2024490156","https://openalex.org/W2048142341","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2141998673","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2476548250","https://openalex.org/W2535388113","https://openalex.org/W2774389566","https://openalex.org/W2889286744","https://openalex.org/W2892356933","https://openalex.org/W2906042495","https://openalex.org/W2937484199","https://openalex.org/W2938901746","https://openalex.org/W2940275453","https://openalex.org/W2943554574","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963446712","https://openalex.org/W3037932933"],"related_works":["https://openalex.org/W4388418691","https://openalex.org/W4379875126","https://openalex.org/W4378977125","https://openalex.org/W2937484199","https://openalex.org/W2939378741","https://openalex.org/W7128774814","https://openalex.org/W3134695619","https://openalex.org/W3013304952","https://openalex.org/W4309833671","https://openalex.org/W3127510418"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"propose":[4,81],"a":[5,98,104,108],"fully":[6],"convolutional":[7,85],"neural":[8],"network":[9,20,74],"for":[10,76,90],"real-time":[11,77,129],"speech":[12],"enhancement":[13],"in":[14,31,53,87,132],"the":[15,32,35,73,88,93,116,123],"time":[16],"domain.":[17],"The":[18,29,49,59,111],"proposed":[19,112,124],"is":[21,95],"an":[22],"encoder-decoder":[23],"based":[24],"architecture":[25],"with":[26,101],"skip":[27],"connections.":[28],"layers":[30,86],"encoder":[33],"and":[34,46,107,137],"decoder":[36,89],"are":[37,62],"followed":[38],"by":[39],"densely":[40],"connected":[41],"blocks":[42],"comprising":[43],"of":[44,134],"dilated":[45,50],"causal":[47,60],"convolutions.":[48],"convolutions":[51,61],"help":[52],"context":[54],"aggregation":[55],"at":[56],"different":[57],"resolutions.":[58],"used":[63],"to":[64,82],"avoid":[65],"information":[66],"flow":[67],"from":[68],"future":[69],"frames,":[70],"hence":[71],"making":[72],"suitable":[75],"applications.":[78],"We":[79],"also":[80],"use":[83],"sub-pixel":[84],"upsampling.":[91],"Further,":[92],"model":[94,125],"trained":[96],"using":[97],"loss":[99,106,113],"function":[100,114],"two":[102],"components;":[103],"time-domain":[105,117],"frequency-domain":[109],"loss.":[110,118],"outperforms":[115,127],"Experimental":[119],"results":[120],"show":[121],"that":[122],"significantly":[126],"other":[128],"state-of-the-art":[130],"models":[131],"terms":[133],"objective":[135],"intelligibility":[136],"quality":[138],"scores.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":30},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":5}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2020-04-17T00:00:00"}