{"id":"https://openalex.org/W3185389098","doi":"https://doi.org/10.1109/waspaa52581.2021.9632756","title":"Controlling the Remixing of Separated Dialogue with a Non-Intrusive Quality Estimate","display_name":"Controlling the Remixing of Separated Dialogue with a Non-Intrusive Quality Estimate","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3185389098","doi":"https://doi.org/10.1109/waspaa52581.2021.9632756","mag":"3185389098"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/2107.10151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Matteo Torcoli","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058"],"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/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"]},{"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":"Jouni Paulus","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058","International Audio Laboratories Erlangen, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210124274"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078888459","display_name":"Thorsten Kastner","orcid":"https://orcid.org/0000-0002-1753-5314"},"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":"Thorsten Kastner","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":"last","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"]},{"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":"Christian Uhle","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058","International Audio Laboratories Erlangen, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210124274"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021417399"],"corresponding_institution_ids":["https://openalex.org/I4210124274"],"apc_list":null,"apc_paid":null,"fwci":1.3998,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84902247,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"48","issue":null,"first_page":"91","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10970","display_name":"Team Dynamics and Performance","score":0.9516000151634216,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6578007936477661},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5509374737739563},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.07359433174133301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6578007936477661},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5509374737739563},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.07359433174133301},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.10151","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.10151","pdf_url":"https://arxiv.org/pdf/2107.10151","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/504804","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/504804","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:2107.10151","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.10151","pdf_url":"https://arxiv.org/pdf/2107.10151","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":37,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1606487971","https://openalex.org/W2105921478","https://openalex.org/W2395718496","https://openalex.org/W2565807767","https://openalex.org/W2590294203","https://openalex.org/W2696558042","https://openalex.org/W2761108741","https://openalex.org/W2771189179","https://openalex.org/W2804772002","https://openalex.org/W2805233667","https://openalex.org/W2889830381","https://openalex.org/W2892110446","https://openalex.org/W2892129657","https://openalex.org/W2943895317","https://openalex.org/W2949558265","https://openalex.org/W2963045393","https://openalex.org/W2963403924","https://openalex.org/W2968860202","https://openalex.org/W2983514941","https://openalex.org/W2987307811","https://openalex.org/W2987989623","https://openalex.org/W2998733532","https://openalex.org/W3015644200","https://openalex.org/W3016050488","https://openalex.org/W3016230310","https://openalex.org/W3103619082","https://openalex.org/W3103902067","https://openalex.org/W3145029257","https://openalex.org/W4226106140","https://openalex.org/W6636045042","https://openalex.org/W6734576452","https://openalex.org/W6740595283","https://openalex.org/W6744463207","https://openalex.org/W6751497725","https://openalex.org/W6762114000","https://openalex.org/W6811551094"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Remixing":[0],"separated":[1,126],"audio":[2,19,52],"sources":[3],"trades":[4],"off":[5],"interferer":[6,183],"attenuation":[7,184],"against":[8],"the":[9,38,62,76,82,105,109,115,125,140,144,178,182,189,193],"amount":[10],"of":[11,61,75,180,192],"audible":[12,197],"deteriorations.":[13],"This":[14],"paper":[15],"proposes":[16],"a":[17,28,186],"non-intrusive":[18,167],"quality":[20,40,53,191],"estimation":[21],"method":[22],"for":[23,156],"controlling":[24],"this":[25,90,207],"trade-off":[26],"in":[27,54,94],"signal-adaptive":[29],"manner.":[30],"The":[31,79,166],"recently":[32],"proposed":[33],"2f-model":[34,80,106],"is":[35,64,91,131,170,208],"adopted":[36],"as":[37,86,118],"underlying":[39],"measure,":[41],"since":[42],"it":[43],"has":[44],"been":[45],"shown":[46,132],"to":[47,103,172,218],"correlate":[48],"strongly":[49],"with":[50,71,139,177,212],"basic":[51],"source":[55,85],"separation.":[56],"An":[57],"alternative":[58],"operation":[59],"mode":[60],"measure":[63,142],"proposed,":[65],"more":[66],"appropriate":[67],"when":[68],"considering":[69],"material":[70],"long":[72],"inactive":[73],"periods":[74],"target":[77,84,111],"source.":[78],"requires":[81],"reference":[83,110,119],"an":[87],"input,":[88],"but":[89,198],"not":[92,199],"available":[93],"many":[95],"applications.":[96],"Deep":[97],"neural":[98],"networks":[99],"(DNNs)":[100],"are":[101],"trained":[102],"estimate":[104,168],"intrusively":[107],"using":[108,114,123],"(iDNN2f),":[112],"non-intrusively":[113],"input":[116],"mix":[117],"(nDNN2f),":[120],"and":[121,161],"reference-free":[122],"only":[124],"output":[127,195],"signal":[128],"(rDNN2f).":[129],"It":[130],"that":[133,206],"iDNN2f":[134],"achieves":[135],"very":[136,213],"strong":[137],"correlation":[138],"original":[141],"on":[143,188],"test":[145,204],"data":[146],"(Pearson":[147],"<tex":[148],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\rho":[150],"=0.99$</tex>":[151],"),":[152],"while":[153],"performance":[154],"decreases":[155],"nDNN2f":[157,169],"(\u03c1":[158,163],"\u2265":[159,164],"0.91)":[160],"rDNN2f":[162],"0.82).":[165],"mapped":[171],"select":[173],"item-dependent":[174],"remixing":[175],"gains":[176,216],"aim":[179],"maximizing":[181],"under":[185],"constraint":[187],"minimum":[190],"remixed":[194],"(e.g.,":[196],"annoying":[200],"deteriorations).":[201],"A":[202],"listening":[203],"shows":[205],"successfully":[209],"achieved":[210],"even":[211],"different":[214],"selected":[215],"(up":[217],"23":[219],"dB":[220],"difference).":[221]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
