{"id":"https://openalex.org/W4386764256","doi":"https://doi.org/10.1109/waspaa58266.2023.10248144","title":"SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement","display_name":"SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386764256","doi":"https://doi.org/10.1109/waspaa58266.2023.10248144"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2312.01744","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050706599","display_name":"M. Strauss","orcid":"https://orcid.org/0000-0003-0610-8250"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Martin Strauss","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039716073","display_name":"Nicola Pia","orcid":"https://orcid.org/0000-0003-0987-863X"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicola Pia","raw_affiliation_strings":["Fraunhofer IIS,Erlangen,Germany","Fraunhofer IIS, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]},{"raw_affiliation_string":"Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048118861","display_name":"Nagashree K. S. Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nagashree K. S. Rao","raw_affiliation_strings":["Fraunhofer IIS,Erlangen,Germany","Fraunhofer IIS, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]},{"raw_affiliation_string":"Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022331149","display_name":"Bernd Edler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Edler","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050706599"],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":0.8004,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71832033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.996999979019165,"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":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7676129341125488},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6734951734542847},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5512418150901794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5251871347427368},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5099667310714722},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.473629891872406},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4501476585865021},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.4468013644218445},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.43517541885375977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.415014386177063},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.38062429428100586},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34085407853126526},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18273836374282837},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11384811997413635},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08715739846229553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676129341125488},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6734951734542847},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5512418150901794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5251871347427368},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5099667310714722},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.473629891872406},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4501476585865021},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.4468013644218445},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.43517541885375977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.415014386177063},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.38062429428100586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34085407853126526},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18273836374282837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11384811997413635},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08715739846229553},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2312.01744","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.01744","pdf_url":"https://arxiv.org/pdf/2312.01744","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"},{"id":"pmh:oai:publica.fraunhofer.de:publica/469521","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/469521","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2312.01744","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2312.01744","pdf_url":"https://arxiv.org/pdf/2312.01744","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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386764256.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2289394825","https://openalex.org/W2516001803","https://openalex.org/W2519091744","https://openalex.org/W2782599016","https://openalex.org/W2791686384","https://openalex.org/W2952218014","https://openalex.org/W2963073614","https://openalex.org/W2963300588","https://openalex.org/W2964058413","https://openalex.org/W2998733532","https://openalex.org/W3015338123","https://openalex.org/W3092028330","https://openalex.org/W3099330747","https://openalex.org/W3121370741","https://openalex.org/W3160324929","https://openalex.org/W3167533889","https://openalex.org/W3197912330","https://openalex.org/W4221143458","https://openalex.org/W4221144097","https://openalex.org/W4226106140","https://openalex.org/W4281820413","https://openalex.org/W4287236406","https://openalex.org/W4289242435","https://openalex.org/W4292387427","https://openalex.org/W4296068829","https://openalex.org/W4297841790","https://openalex.org/W4319862640","https://openalex.org/W4380434618","https://openalex.org/W6756251360","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W2773393136"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"SEFGAN,":[3],"a":[4,25,39,46,63,109],"Deep":[5],"Neural":[6],"Network":[7],"(DNN)":[8],"combining":[9],"maximum":[10,67],"likelihood":[11,53,68],"training":[12,69],"and":[13,55,66,80,108],"Generative":[14],"Adversarial":[15],"Networks":[16],"(GANs)":[17],"for":[18],"efficient":[19],"speech":[20,33,37],"enhancement":[21,101],"(SE).":[22],"For":[23],"this,":[24],"DNN":[26],"is":[27,57,115],"trained":[28],"to":[29,74,99],"synthesize":[30],"the":[31,50,72,91,100],"enhanced":[32],"conditioned":[34],"on":[35],"noisy":[36],"using":[38,105],"Normalizing":[40],"Flow":[41],"(NF)":[42],"as":[43],"generator":[44],"in":[45],"GAN":[47],"framework.":[48],"While":[49],"combination":[51],"of":[52],"models":[54],"GANs":[56],"not":[58],"trivial,":[59],"SEFGAN":[60,114],"demonstrates":[61],"that":[62,86,113],"hybrid":[64],"adversarial":[65],"approach":[70,88],"enables":[71],"model":[73,94],"maintain":[75],"high":[76],"quality":[77],"audio":[78],"generation":[79],"log-likelihood":[81],"estimation.":[82],"Our":[83],"experiments":[84],"indicate":[85],"this":[87],"strongly":[89],"outperforms":[90],"baseline":[92],"NF-based":[93],"without":[95],"introducing":[96],"additional":[97],"complexity":[98],"network.":[102],"A":[103],"comparison":[104],"computational":[106],"metrics":[107],"listening":[110],"experiment":[111],"reveals":[112],"competitive":[116],"with":[117],"other":[118],"state-of-the-art":[119],"models.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}