{"id":"https://openalex.org/W3049430014","doi":"https://doi.org/10.1109/taslp.2020.3016487","title":"On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement","display_name":"On Cross-Corpus Generalization of Deep Learning Based Speech Enhancement","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3049430014","doi":"https://doi.org/10.1109/taslp.2020.3016487","mag":"3049430014","pmid":"https://pubmed.ncbi.nlm.nih.gov/33748327"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3016487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3016487","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/7971413","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":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, 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, 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, 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, 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":5.9392,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.97265625,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"2489","last_page":"2499"},"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":0.9983999729156494,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9954000115394592,"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/normalization","display_name":"Normalization (sociology)","score":0.7847526669502258},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7475450038909912},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6980708241462708},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6792055368423462},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.567900538444519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5472937226295471},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5329502820968628},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5009787082672119},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.46381041407585144},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38022664189338684},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.36835333704948425},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3622969388961792},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3238859176635742},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17927122116088867},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1510435938835144},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.12345823645591736}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7847526669502258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475450038909912},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6980708241462708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6792055368423462},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.567900538444519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472937226295471},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5329502820968628},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5009787082672119},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.46381041407585144},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38022664189338684},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.36835333704948425},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3622969388961792},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3238859176635742},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17927122116088867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1510435938835144},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.12345823645591736},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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.2020.3016487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3016487","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:33748327","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33748327","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:7971413","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971413","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:7971413","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7971413","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"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"},{"id":"https://openalex.org/G3481055361","display_name":null,"funder_award_id":"R01 DC015521","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"},{"id":"https://openalex.org/G5601408477","display_name":null,"funder_award_id":"R01DC015521","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":56,"referenced_works":["https://openalex.org/W157872538","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1897240248","https://openalex.org/W1974387177","https://openalex.org/W2013608223","https://openalex.org/W2024490156","https://openalex.org/W2029757964","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2069976350","https://openalex.org/W2112180173","https://openalex.org/W2114218864","https://openalex.org/W2128653836","https://openalex.org/W2137075158","https://openalex.org/W2141998673","https://openalex.org/W2153894152","https://openalex.org/W2165899180","https://openalex.org/W2168379380","https://openalex.org/W2168548156","https://openalex.org/W2168961642","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2516342150","https://openalex.org/W2552071709","https://openalex.org/W2678916739","https://openalex.org/W2747161606","https://openalex.org/W2774389566","https://openalex.org/W2808631503","https://openalex.org/W2890820256","https://openalex.org/W2892356933","https://openalex.org/W2897371647","https://openalex.org/W2937484199","https://openalex.org/W2938901746","https://openalex.org/W2940275453","https://openalex.org/W2943554574","https://openalex.org/W2949756029","https://openalex.org/W2962866211","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963828919","https://openalex.org/W2964121744","https://openalex.org/W2991361823","https://openalex.org/W4231807801","https://openalex.org/W4253928870","https://openalex.org/W6606433532","https://openalex.org/W6631190155","https://openalex.org/W6639532686","https://openalex.org/W6726607834","https://openalex.org/W6735429107","https://openalex.org/W6743354777","https://openalex.org/W6746567100","https://openalex.org/W6757632829"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W4287755480","https://openalex.org/W2542062716","https://openalex.org/W2402466562","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W3113607506","https://openalex.org/W4297779039"],"abstract_inverted_index":{"In":[0,58],"recent":[1],"years,":[2],"supervised":[3],"approaches":[4],"using":[5,32,126],"deep":[6],"neural":[7],"networks":[8],"(DNNs)":[9],"have":[10],"become":[11],"the":[12,64,72,80,167],"mainstream":[13],"for":[14,109],"speech":[15,50,135],"enhancement.":[16],"It":[17],"has":[18],"been":[19],"established":[20],"that":[21,43,63,88,106,125],"DNNs":[22,44],"generalize":[23,47],"well":[24],"to":[25,46,48,71,116,144],"untrained":[26,83,174],"noises":[27,37],"and":[28,38,82,154,170],"speakers":[29],"if":[30],"trained":[31,81],"a":[33,127],"large":[34],"number":[35],"of":[36,66,134],"speakers.":[39],"However,":[40],"we":[41,61,86,101,123],"find":[42,112,124],"fail":[45],"new":[49],"corpora":[51,175],"in":[52,96,131,158],"low":[53],"signal-to-noise":[54],"ratio":[55],"(SNR)":[56],"conditions.":[57],"this":[59],"work,":[60],"establish":[62],"lack":[65],"generalization":[67,147],"is":[68],"mainly":[69],"due":[70],"channel":[73,90,149],"mismatch,":[74],"i.e.":[75],"different":[76],"recording":[77],"conditions":[78],"between":[79],"corpus.":[84],"Additionally,":[85],"observe":[87],"traditional":[89],"normalization":[91],"techniques":[92,143,164],"are":[93,107],"not":[94],"effective":[95],"improving":[97],"cross-corpus":[98,139,146],"generalization.":[99,110,140],"Further,":[100],"evaluate":[102],"publicly":[103],"available":[104],"datasets":[105],"promising":[108],"We":[111],"one":[113],"particular":[114],"corpus":[115],"be":[117],"significantly":[118,137],"better":[119,151],"than":[120],"others.":[121],"Finally,":[122],"smaller":[128,155],"frame":[129,156],"shift":[130,157],"short-time":[132,159],"processing":[133],"can":[136],"improve":[138,166],"The":[141],"proposed":[142],"address":[145],"include":[148],"normalization,":[150],"training":[152],"corpus,":[153],"Fourier":[160],"transform":[161],"(STFT).":[162],"These":[163],"together":[165],"objective":[168],"intelligibility":[169],"quality":[171],"scores":[172],"on":[173],"significantly.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":5}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
