{"id":"https://openalex.org/W4319862640","doi":"https://doi.org/10.1109/slt54892.2023.10022898","title":"Improved Normalizing Flow-Based Speech Enhancement Using an all-Pole Gammatone Filterbank for Conditional Input Representation","display_name":"Improved Normalizing Flow-Based Speech Enhancement Using an all-Pole Gammatone Filterbank for Conditional Input Representation","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862640","doi":"https://doi.org/10.1109/slt54892.2023.10022898"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022898","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022898","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/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"]},{"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":"Martin Strauss","raw_affiliation_strings":["Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Fraunhofer IIS,International Audio Laboratories,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Fraunhofer IIS,International Audio Laboratories,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021417399","display_name":"Matteo Torcoli","orcid":"https://orcid.org/0000-0003-2834-9194"},"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"]},{"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":"Matteo Torcoli","raw_affiliation_strings":["Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Fraunhofer IIS,International Audio Laboratories,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Fraunhofer IIS,International Audio Laboratories,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192","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"]},{"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":"Bernd Edler","raw_affiliation_strings":["Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Fraunhofer IIS,International Audio Laboratories,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Fraunhofer IIS,International Audio Laboratories,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1517,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78654971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9988999962806702,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.7246260046958923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6941356658935547},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5818088054656982},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.544446587562561},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5432568192481995},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4972265064716339},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4895997643470764},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41952186822891235},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4157432019710541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34748804569244385},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33688563108444214},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.23413875699043274},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18172135949134827},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11405062675476074}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7246260046958923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6941356658935547},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5818088054656982},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.544446587562561},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5432568192481995},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4972265064716339},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4895997643470764},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41952186822891235},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4157432019710541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34748804569244385},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33688563108444214},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.23413875699043274},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18172135949134827},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11405062675476074},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt54892.2023.10022898","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022898","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/448512","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/448512","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":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W38275695","https://openalex.org/W2067295501","https://openalex.org/W2094721231","https://openalex.org/W2113131123","https://openalex.org/W2126554103","https://openalex.org/W2131754512","https://openalex.org/W2144404214","https://openalex.org/W2514828952","https://openalex.org/W2519091744","https://openalex.org/W2531409750","https://openalex.org/W2747161606","https://openalex.org/W2791686384","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963300588","https://openalex.org/W2998733532","https://openalex.org/W3005621653","https://openalex.org/W3011982609","https://openalex.org/W3086154751","https://openalex.org/W3099330747","https://openalex.org/W3142252347","https://openalex.org/W3145029257","https://openalex.org/W3150807214","https://openalex.org/W3151851237","https://openalex.org/W3160324929","https://openalex.org/W3161236344","https://openalex.org/W3167533889","https://openalex.org/W3177067699","https://openalex.org/W3197676764","https://openalex.org/W3197912330","https://openalex.org/W4200483526","https://openalex.org/W4212774754","https://openalex.org/W4221144097","https://openalex.org/W4225873749","https://openalex.org/W4232282348","https://openalex.org/W4253928870","https://openalex.org/W6601558732","https://openalex.org/W6714644935","https://openalex.org/W6729767818","https://openalex.org/W6752910514","https://openalex.org/W6753758835","https://openalex.org/W6770847983","https://openalex.org/W6783713337"],"related_works":["https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W3178813832","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4226298148","https://openalex.org/W2972144487","https://openalex.org/W4235873501"],"abstract_inverted_index":{"Deep":[0],"generative":[1],"models":[2],"for":[3,62],"Speech":[4],"Enhancement":[5],"(SE)":[6],"received":[7,26],"increasing":[8],"attention":[9,28],"in":[10,54],"recent":[11],"years.":[12],"The":[13],"most":[14],"prominent":[15],"example":[16],"are":[17,38,121],"Generative":[18],"Adversarial":[19],"Networks":[20],"(GANs),":[21],"while":[22],"normalizing":[23],"flows":[24],"(NF)":[25],"less":[27],"despite":[29],"their":[30],"potential.":[31],"Building":[32],"on":[33,106],"previous":[34],"work,":[35],"architectural":[36],"modifications":[37],"proposed,":[39],"along":[40],"with":[41,73],"an":[42],"investigation":[43],"of":[44],"different":[45],"conditional":[46],"input":[47],"representations.":[48],"Despite":[49],"being":[50],"a":[51,67,92,96],"common":[52],"choice":[53],"related":[55],"works,":[56],"Mel-spectrograms":[57],"demonstrate":[58],"to":[59],"be":[60],"inadequate":[61],"the":[63,101,131],"given":[64],"scenario.":[65],"Alternatively,":[66],"novel":[68],"All-Pole":[69],"Gammatone":[70],"filterbank":[71],"(APG)":[72],"high":[74],"temporal":[75],"resolution":[76],"is":[77,128],"proposed.":[78],"Although":[79],"computational":[80],"evaluation":[81,94],"metric":[82],"results":[83],"would":[84],"suggest":[85],"that":[86,100],"state-of-the-art":[87],"GAN-based":[88],"methods":[89],"perform":[90],"best,":[91,112],"perceptual":[93],"via":[95],"listening":[97],"test":[98],"indicates":[99],"presented":[102],"NF":[103],"approach":[104],"(based":[105],"time":[107],"domain":[108],"and":[109],"APG)":[110],"performs":[111],"especially":[113],"at":[114],"lower":[115],"SNRs.":[116],"On":[117],"average,":[118],"APG":[119],"outputs":[120],"rated":[122],"as":[123],"having":[124],"good":[125],"quality,":[126],"which":[127],"unmatched":[129],"by":[130],"other":[132],"methods,":[133],"including":[134],"GAN.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2023-02-11T00:00:00"}