{"id":"https://openalex.org/W2937484199","doi":"https://doi.org/10.1109/icassp.2019.8683634","title":"TCNN: Temporal Convolutional Neural Network for Real-time Speech Enhancement in the Time Domain","display_name":"TCNN: Temporal Convolutional Neural Network for Real-time Speech Enhancement in the Time Domain","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2937484199","doi":"https://doi.org/10.1109/icassp.2019.8683634","mag":"2937484199"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"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"},"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"},"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":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, 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":null,"has_fulltext":false,"cited_by_count":392,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6875","last_page":"6879"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8706637620925903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7969986200332642},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7028930187225342},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.5662731528282166},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5476471781730652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5411765575408936},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.5355707406997681},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4650837779045105},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.449429452419281},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42961281538009644},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41974806785583496},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.29210638999938965},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28542622923851013},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.21515342593193054},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0734952986240387}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8706637620925903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7969986200332642},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7028930187225342},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.5662731528282166},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5476471781730652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5411765575408936},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.5355707406997681},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4650837779045105},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.449429452419281},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42961281538009644},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41974806785583496},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29210638999938965},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28542622923851013},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.21515342593193054},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0734952986240387},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683634","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683634","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1836465849","https://openalex.org/W2013608223","https://openalex.org/W2024490156","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2153894152","https://openalex.org/W2194775991","https://openalex.org/W2531409750","https://openalex.org/W2792764867","https://openalex.org/W2889286744","https://openalex.org/W2889442120","https://openalex.org/W2892365986","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2963828919","https://openalex.org/W2964121744","https://openalex.org/W3120418020","https://openalex.org/W4253928870","https://openalex.org/W6631190155","https://openalex.org/W6633117090","https://openalex.org/W6638667902","https://openalex.org/W6749825310","https://openalex.org/W6754743415"],"related_works":["https://openalex.org/W1445015017","https://openalex.org/W2920938200","https://openalex.org/W2765889516","https://openalex.org/W2415731916","https://openalex.org/W2342591535","https://openalex.org/W2937484199","https://openalex.org/W2587789887","https://openalex.org/W2995001040","https://openalex.org/W2726408216","https://openalex.org/W3123880622"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"a":[3,43,55,60,100,118],"fully":[4,129],"convolutional":[5,29,70,121],"neural":[6],"network":[7],"(CNN)":[8],"for":[9],"real-time":[10,120],"speech":[11],"enhancement":[12,115],"in":[13,51,99],"the":[14,34,37,52,74,78,86,91,109,126],"time":[15],"domain.":[16],"The":[17,49,64,83,94],"proposed":[18,95,110],"CNN":[19],"is":[20,97,128],"an":[21,26],"encoder-decoder":[22],"based":[23],"architecture":[24,42],"with":[25],"additional":[27],"temporal":[28],"module":[30],"(TCM)":[31],"inserted":[32],"between":[33],"encoder":[35,50,75],"and":[36,68,80,102],"decoder.":[38],"We":[39],"call":[40],"this":[41],"Temporal":[44],"Convolutional":[45],"Neural":[46],"Network":[47],"(TCNN).":[48],"TCNN":[53],"creates":[54],"low":[56],"dimensional":[57],"representation":[58],"of":[59,77],"noisy":[61],"input":[62],"frame.":[63,93],"TCM":[65,87],"uses":[66,85],"causal":[67],"dilated":[69],"layers":[71],"to":[72,89],"utilize":[73],"output":[76,88],"current":[79],"previous":[81],"frames.":[82],"decoder":[84],"reconstruct":[90],"enhanced":[92],"model":[96,111,127],"trained":[98],"speaker-":[101],"noise-independent":[103],"way.":[104],"Experimental":[105],"results":[106,116],"demonstrate":[107],"that":[108],"gives":[112],"consistently":[113],"better":[114],"than":[117,137],"state-of-the-art":[119],"recurrent":[122],"model.":[123],"Moreover,":[124],"since":[125],"convolutional,":[130],"it":[131],"has":[132],"much":[133],"fewer":[134],"trainable":[135],"parameters":[136],"earlier":[138],"models.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":70},{"year":2023,"cited_by_count":80},{"year":2022,"cited_by_count":61},{"year":2021,"cited_by_count":71},{"year":2020,"cited_by_count":44},{"year":2019,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}