{"id":"https://openalex.org/W2943554574","doi":"https://doi.org/10.1109/taslp.2019.2913512","title":"A New Framework for CNN-Based Speech Enhancement in the Time Domain","display_name":"A New Framework for CNN-Based Speech Enhancement in the Time Domain","publication_year":2019,"publication_date":"2019-04-29","ids":{"openalex":"https://openalex.org/W2943554574","doi":"https://doi.org/10.1109/taslp.2019.2913512","mag":"2943554574","pmid":"https://pubmed.ncbi.nlm.nih.gov/34262993","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/8276831"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2913512","doi":"https://doi.org/10.1109/taslp.2019.2913512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2913512","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,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8276831","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","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, Columbus, OH 43210 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-3352-7453","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","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 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"],"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 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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":24.1223,"has_fulltext":false,"cited_by_count":301,"citation_normalized_percentile":{"value":0.99787543,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"27","issue":"7","first_page":"1179","last_page":"1188"},"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":0.00019999999494757503,"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/T10688","display_name":"Image and Signal Denoising Methods","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9940000176429749},{"id":"https://openalex.org/keywords/time-domain-speech-enhancement","display_name":"time-domain speech enhancement","score":0.8090000152587891},{"id":"https://openalex.org/keywords/fully-convolutional-network","display_name":"fully convolutional network","score":0.8450000286102295},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"short-time Fourier transform","score":0.8220000267028809},{"id":"https://openalex.org/keywords/frequency-domain-loss","display_name":"frequency domain loss","score":0.7910000085830688},{"id":"https://openalex.org/keywords/time-frequency-masking","display_name":"time-frequency masking","score":0.5910000205039978},{"id":"https://openalex.org/keywords/spectral-mapping","display_name":"spectral mapping","score":0.8429999947547913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8296726942062378},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.70308518409729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6310802102088928},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.584547758102417},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5525988936424255},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.535919189453125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310369729995728},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5026485919952393},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4987032413482666},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4713033139705658},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4360063672065735},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.421498566865921},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42083922028541565},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4142616391181946},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4035840928554535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13686665892601013},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.11539047956466675},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11423459649085999},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10581323504447937},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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.2019.2913512","doi":"https://doi.org/10.1109/taslp.2019.2913512","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2913512","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,"listed_in":["ccf-b","cwts-core","dongbi-a","norway-2","poland-140","russia-white-list-1"],"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:34262993","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34262993","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,"listed_in":[],"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":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8276831","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8276831","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,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"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:8276831","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8276831","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,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5699999928474426}],"study_designs":[],"awards":[{"id":"https://openalex.org/G4343214945","display_name":null,"funder_award_id":"R02 DCDC015521","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G6572069668","display_name":"Speech segregation to improve intelligility of reverberant-noisy speech","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1516630152","https://openalex.org/W1522301498","https://openalex.org/W1525783482","https://openalex.org/W1533861849","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1677182931","https://openalex.org/W1745334888","https://openalex.org/W1899504021","https://openalex.org/W1901129140","https://openalex.org/W1974387177","https://openalex.org/W2006129368","https://openalex.org/W2024490156","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2095705004","https://openalex.org/W2120847449","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2156379660","https://openalex.org/W2165899180","https://openalex.org/W2168379380","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2405774341","https://openalex.org/W2519091744","https://openalex.org/W2526733715","https://openalex.org/W2561557072","https://openalex.org/W2600556233","https://openalex.org/W2678916739","https://openalex.org/W2747161606","https://openalex.org/W2774389566","https://openalex.org/W2889286744","https://openalex.org/W2891355459","https://openalex.org/W2892356933","https://openalex.org/W2892365986","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2963045393","https://openalex.org/W2963103134","https://openalex.org/W2963828919","https://openalex.org/W2964121744","https://openalex.org/W3127686677","https://openalex.org/W4231807801","https://openalex.org/W4253928870","https://openalex.org/W4320013936","https://openalex.org/W6743354777"],"related_works":["https://openalex.org/W3043944970","https://openalex.org/W2937484199","https://openalex.org/W3099283299","https://openalex.org/W4391486999","https://openalex.org/W4206609401","https://openalex.org/W3134695619","https://openalex.org/W4328027768","https://openalex.org/W3089552252","https://openalex.org/W7103651174","https://openalex.org/W3034763882"],"abstract_inverted_index":{"This":[0,60,109],"paper":[1],"proposes":[2],"a":[3,8,73,120],"new":[4],"learning":[5],"mechanism":[6],"for":[7,80,126],"fully":[9],"convolutional":[10],"neural":[11],"network":[12],"(CNN)":[13],"to":[14,56,63,105,122,166,170],"address":[15],"speech":[16,159,172],"enhancement":[17],"in":[18,82,142],"the":[19,27,35,39,43,53,57,83,93,101,107,111,115,123,132,138,143,150,155],"time":[20,28,36,54,84,144],"domain.":[21,59,85,145],"The":[22,161],"CNN":[23,140],"takes":[24],"as":[25],"input":[26],"frames":[29,37],"of":[30,38,118,158],"noisy":[31],"utterance":[32],"and":[33,67,100,168],"outputs":[34],"enhanced":[40,94],"utterance.":[41],"At":[42],"training":[44,81],"time,":[45],"we":[46],"add":[47],"an":[48],"extra":[49],"operation":[50],"that":[51,72,149,175],"converts":[52],"domain":[55,75,116,125],"frequency":[58,74,124],"conversion":[61],"corresponds":[62],"simple":[64],"matrix":[65],"multiplication,":[66],"is":[68,164],"hence":[69],"differentiable":[70],"implying":[71],"loss":[76,91],"can":[77,113],"be":[78],"used":[79],"We":[86],"use":[87],"mean":[88],"absolute":[89],"error":[90],"between":[92],"short-time":[95],"Fourier":[96],"transform":[97],"(STFT)":[98],"magnitude":[99,104],"clean":[102],"STFT":[103,135],"train":[106],"CNN.":[108],"way,":[110],"model":[112],"exploit":[114],"knowledge":[117],"converting":[119],"signal":[121],"analysis.":[127],"Moreover,":[128],"this":[129],"approach":[130],"avoids":[131],"well-known":[133],"invalid":[134],"problem":[136],"since":[137],"proposed":[139,151,162],"operates":[141],"Experimental":[146],"results":[147],"demonstrate":[148],"method":[152,163],"substantially":[153],"outperforms":[154],"other":[156],"methods":[157],"enhancement.":[160],"easy":[165],"implement":[167],"applicable":[169],"related":[171],"processing":[173],"tasks":[174],"require":[176],"time-frequency":[177],"masking":[178],"or":[179],"spectral":[180],"mapping.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":53},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":62},{"year":2020,"cited_by_count":44},{"year":2019,"cited_by_count":5}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2019-05-09T00:00:00"}