{"id":"https://openalex.org/W3016230310","doi":"https://doi.org/10.1109/icassp40776.2020.9053789","title":"Controlling the Perceived Sound Quality for Dialogue Enhancement With Deep Learning","display_name":"Controlling the Perceived Sound Quality for Dialogue Enhancement With Deep Learning","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016230310","doi":"https://doi.org/10.1109/icassp40776.2020.9053789","mag":"3016230310"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.10562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001119038","display_name":"Christian Uhle","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":"Christian Uhle","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058","institution_ids":["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/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":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054389422","display_name":"Jouni Paulus","orcid":"https://orcid.org/0000-0003-2283-2062"},"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":"Jouni Paulus","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4562,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59887816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"51","last_page":"55"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.7285184264183044},{"id":"https://openalex.org/keywords/attenuation","display_name":"Attenuation","score":0.6391905546188354},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.6290133595466614},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.6099312901496887},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6008305549621582},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.5872509479522705},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5550169348716736},{"id":"https://openalex.org/keywords/sound-perception","display_name":"Sound perception","score":0.5500081181526184},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5424706339836121},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5312516689300537},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.49741414189338684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4234238266944885},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2875520884990692},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1330050230026245},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08660849928855896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285184264183044},{"id":"https://openalex.org/C184652730","wikidata":"https://www.wikidata.org/wiki/Q2357982","display_name":"Attenuation","level":2,"score":0.6391905546188354},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.6290133595466614},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.6099312901496887},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6008305549621582},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.5872509479522705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5550169348716736},{"id":"https://openalex.org/C3019767756","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Sound perception","level":3,"score":0.5500081181526184},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5424706339836121},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5312516689300537},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.49741414189338684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4234238266944885},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2875520884990692},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1330050230026245},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08660849928855896},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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":4,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.10562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.10562","pdf_url":"https://arxiv.org/pdf/2107.10562","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:fraunhofer.de:N-602759","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-602759.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (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":"Fraunhofer IIS","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/408882","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/408882","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:2107.10562","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.10562","pdf_url":"https://arxiv.org/pdf/2107.10562","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1555479677","https://openalex.org/W1588397041","https://openalex.org/W1968521648","https://openalex.org/W1973538555","https://openalex.org/W2032751712","https://openalex.org/W2105921478","https://openalex.org/W2108708552","https://openalex.org/W2110120390","https://openalex.org/W2121973264","https://openalex.org/W2127851351","https://openalex.org/W2138456300","https://openalex.org/W2320327404","https://openalex.org/W2321005578","https://openalex.org/W2395718496","https://openalex.org/W2565807767","https://openalex.org/W2696558042","https://openalex.org/W2771189179","https://openalex.org/W2804772002","https://openalex.org/W2805233667","https://openalex.org/W2806010960","https://openalex.org/W2891607145","https://openalex.org/W2963045393","https://openalex.org/W2968860202","https://openalex.org/W2983514941","https://openalex.org/W3103619082","https://openalex.org/W3147539069","https://openalex.org/W4252164768","https://openalex.org/W6633191696","https://openalex.org/W6680701378","https://openalex.org/W6751497725","https://openalex.org/W6756181233"],"related_works":["https://openalex.org/W1972388827","https://openalex.org/W2016879054","https://openalex.org/W4399013759","https://openalex.org/W2043889795","https://openalex.org/W3017153150","https://openalex.org/W3201396809","https://openalex.org/W2371230498","https://openalex.org/W2330744077","https://openalex.org/W193850549","https://openalex.org/W2616940542"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,102],"attenuates":[2],"interfering":[3,31],"sounds":[4],"in":[5],"speech":[6],"signals":[7],"but":[8],"may":[9],"introduce":[10],"artifacts":[11],"that":[12,53,70,83,96],"perceivably":[13],"deteriorate":[14],"the":[15,24,27,30,35,45,48,54,59,84,91],"output":[16],"signal.":[17],"We":[18],"propose":[19],"a":[20],"method":[21,86],"for":[22,99],"controlling":[23],"trade-off":[25],"between":[26],"attenuation":[28,46],"of":[29,37,47],"background":[32,50],"signal":[33,51],"and":[34],"loss":[36],"sound":[38,55,72],"quality.":[39],"A":[40],"deep":[41],"neural":[42],"network":[43],"estimates":[44],"separated":[49],"such":[52],"quality,":[56],"quantified":[57],"using":[58],"Artifact-related":[60],"Perceptual":[61],"Score,":[62],"meets":[63],"an":[64,94],"adjustable":[65],"target.":[66],"Subjective":[67],"evaluations":[68],"indicate":[69],"consistent":[71],"quality":[73],"is":[74,87,97],"obtained":[75],"across":[76],"various":[77],"input":[78],"signals.":[79],"Our":[80],"experiments":[81],"show":[82],"proposed":[85],"able":[88],"to":[89],"control":[90],"tradeoff":[92],"with":[93],"accuracy":[95],"adequate":[98],"real-world":[100],"dialogue":[101],"applications.":[103]},"counts_by_year":[{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
