{"id":"https://openalex.org/W3015969340","doi":"https://doi.org/10.1109/taslp.2021.3082702","title":"SNR-Based Features and Diverse Training Data for Robust DNN-Based Speech Enhancement","display_name":"SNR-Based Features and Diverse Training Data for Robust DNN-Based Speech Enhancement","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3015969340","doi":"https://doi.org/10.1109/taslp.2021.3082702","mag":"3015969340"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3082702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3082702","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.03512","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041108140","display_name":"Robert Rehr","orcid":"https://orcid.org/0000-0001-7458-2320"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robert Rehr","raw_affiliation_strings":["Signal Processing Group, Department of Informatics, Universit\u00e4t Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7458-2320","affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Informatics, Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Signal Processing Group, Department of Informatics, Universit\u00e4t Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8678-4699","affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Informatics, Universit\u00e4t Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.934,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91410591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1937","last_page":"1949"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.7779203057289124},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6560118794441223},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6484837532043457},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5391889214515686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5378047823905945},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5306609869003296},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5171124935150146},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4680580496788025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46247541904449463},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.44380664825439453},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43560561537742615},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.431487113237381},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.42994093894958496},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41148656606674194},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.383897066116333},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.258448988199234},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.104575514793396},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06340464949607849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7779203057289124},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6560118794441223},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6484837532043457},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5391889214515686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5378047823905945},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5306609869003296},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5171124935150146},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4680580496788025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46247541904449463},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.44380664825439453},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43560561537742615},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.431487113237381},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.42994093894958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41148656606674194},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.383897066116333},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.258448988199234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.104575514793396},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06340464949607849},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3082702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3082702","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":"pmh:oai:arXiv.org:2004.03512","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.03512","pdf_url":"https://arxiv.org/pdf/2004.03512","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.03512","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.03512","pdf_url":"https://arxiv.org/pdf/2004.03512","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":99,"referenced_works":["https://openalex.org/W126576427","https://openalex.org/W1482149378","https://openalex.org/W1533861849","https://openalex.org/W1552516442","https://openalex.org/W1875842236","https://openalex.org/W1897240248","https://openalex.org/W1963950237","https://openalex.org/W1964509438","https://openalex.org/W1974387177","https://openalex.org/W1988115241","https://openalex.org/W1989364685","https://openalex.org/W1995190897","https://openalex.org/W2013608223","https://openalex.org/W2016254085","https://openalex.org/W2016874282","https://openalex.org/W2018026382","https://openalex.org/W2025515167","https://openalex.org/W2025611902","https://openalex.org/W2042071805","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2051428568","https://openalex.org/W2062164080","https://openalex.org/W2063157319","https://openalex.org/W2064675550","https://openalex.org/W2069486713","https://openalex.org/W2069681747","https://openalex.org/W2078305645","https://openalex.org/W2098301339","https://openalex.org/W2103135337","https://openalex.org/W2103747981","https://openalex.org/W2114780615","https://openalex.org/W2121973264","https://openalex.org/W2127180234","https://openalex.org/W2128653836","https://openalex.org/W2130476329","https://openalex.org/W2144739192","https://openalex.org/W2145310550","https://openalex.org/W2148154194","https://openalex.org/W2149535104","https://openalex.org/W2156387975","https://openalex.org/W2158336491","https://openalex.org/W2159202424","https://openalex.org/W2163195137","https://openalex.org/W2164432048","https://openalex.org/W2164715564","https://openalex.org/W2167090878","https://openalex.org/W2169147844","https://openalex.org/W2187089797","https://openalex.org/W2236045036","https://openalex.org/W2285420822","https://openalex.org/W2286245326","https://openalex.org/W2289394825","https://openalex.org/W2290318471","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2397226255","https://openalex.org/W2399672261","https://openalex.org/W2403766732","https://openalex.org/W2405774341","https://openalex.org/W2507424718","https://openalex.org/W2515930231","https://openalex.org/W2516001803","https://openalex.org/W2519091744","https://openalex.org/W2532854561","https://openalex.org/W2550397165","https://openalex.org/W2559809918","https://openalex.org/W2560174002","https://openalex.org/W2605589342","https://openalex.org/W2606806821","https://openalex.org/W2620676623","https://openalex.org/W2678916739","https://openalex.org/W2746457594","https://openalex.org/W2747161606","https://openalex.org/W2791874741","https://openalex.org/W2938737578","https://openalex.org/W2949382160","https://openalex.org/W2962843322","https://openalex.org/W2962946126","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W3013517569","https://openalex.org/W3049430014","https://openalex.org/W3127686677","https://openalex.org/W3147539069","https://openalex.org/W4245923654","https://openalex.org/W4256217162","https://openalex.org/W4301350573","https://openalex.org/W6605266330","https://openalex.org/W6631943919","https://openalex.org/W6633036220","https://openalex.org/W6682889407","https://openalex.org/W6683207941","https://openalex.org/W6696830301","https://openalex.org/W6712317276","https://openalex.org/W6713298849","https://openalex.org/W6713658392","https://openalex.org/W6738494546","https://openalex.org/W6775736700"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416","https://openalex.org/W3000197790"],"abstract_inverted_index":{"In":[0],"this":[1,196],"paper,":[2],"we":[3,35,63,97,112,150],"address":[4,61,95,110],"the":[5,20,37,43,48,57,67,73,126,165,192],"generalization":[6,38],"of":[7,47,195],"deep":[8],"neural":[9],"network":[10,53,143,181],"(DNN)":[11],"based":[12,89,130],"speech":[13],"enhancement":[14],"to":[15,41,147],"unseen":[16,176],"noise":[17,69,76,121,131,177],"conditions":[18],"for":[19],"case":[21],"that":[22,137,164],"training":[23,49,123,133,139],"data":[24,140],"is":[25,191],"limited":[26],"in":[27,175],"size":[28,44],"and":[29,45,55,80,85,102,125,141,155,171,183],"diversity.":[30],"To":[31,60,94,109],"gain":[32],"more":[33],"insights,":[34],"analyze":[36],"with":[39,179],"respect":[40],"(1)":[42],"diversity":[46],"data,":[50],"(2)":[51],"different":[52],"architectures,":[54],"(3)":[56],"chosen":[58],"features.":[59],"(1),":[62],"train":[64],"networks":[65],"on":[66,90,186],"Hu":[68],"corpus":[70,77],"(limited":[71,78],"size),":[72],"CHiME":[74],"3":[75],"diversity)":[79],"also":[81],"propose":[82],"a":[83,99,103],"large":[84],"diverse":[86],"dataset":[87],"collected":[88],"freely":[91],"available":[92],"sounds.":[93],"(2),":[96],"compare":[98,113],"fully-connected":[100],"feed-forward":[101],"long":[104],"short-term":[105],"memory":[106],"(LSTM)":[107],"architecture.":[108],"(3),":[111],"three":[114],"input":[115],"features,":[116],"namely":[117],"logarithmized":[118],"noisy":[119],"periodograms,":[120],"aware":[122,132],"(NAT)":[124],"proposed":[127,166],"signal-to-noise":[128],"ratio":[129],"(SNR-NAT).":[134],"We":[135],"confirm":[136],"rich":[138],"improved":[142],"architectures":[144,182],"help":[145],"DNNs":[146],"generalize.":[148],"Furthermore,":[149],"show":[151],"via":[152],"experimental":[153],"results":[154,174],"an":[156],"analysis":[157],"using":[158],"t-distributed":[159],"stochastic":[160],"neighbor":[161],"embedding":[162],"(t-SNE)":[163],"SNR-NAT":[167],"features":[168],"yield":[169],"robust":[170],"level":[172],"independent":[173],"even":[178],"simple":[180],"when":[184],"trained":[185],"only":[187],"small":[188],"datasets,":[189],"which":[190],"key":[193],"contribution":[194],"paper.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}