{"id":"https://openalex.org/W3088490496","doi":"https://doi.org/10.1109/tsp52935.2021.9522648","title":"A consolidated view of loss functions for supervised deep learning-based speech enhancement","display_name":"A consolidated view of loss functions for supervised deep learning-based speech enhancement","publication_year":2021,"publication_date":"2021-07-26","ids":{"openalex":"https://openalex.org/W3088490496","doi":"https://doi.org/10.1109/tsp52935.2021.9522648","mag":"3088490496"},"language":"en","primary_location":{"id":"doi:10.1109/tsp52935.2021.9522648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp52935.2021.9522648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 44th International Conference on Telecommunications and Signal Processing (TSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.12286","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055277441","display_name":"Sebastian Braun","orcid":"https://orcid.org/0000-0001-9060-223X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Sebastian Braun","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ivan Tashev","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","(Microsoft)"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055277441"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":1.8468,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85222468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"72","last_page":"76"},"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/T11447","display_name":"Blind Source Separation Techniques","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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"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":0.7326861619949341},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5997486710548401},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5794571042060852},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.523219108581543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4914819002151489},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4868985712528229},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.47621139883995056},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45600947737693787},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4168984293937683},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4068334400653839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4040111303329468},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37830275297164917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326861619949341},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5997486710548401},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5794571042060852},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.523219108581543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4914819002151489},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4868985712528229},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.47621139883995056},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45600947737693787},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4168984293937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4068334400653839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4040111303329468},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37830275297164917},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tsp52935.2021.9522648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp52935.2021.9522648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 44th International Conference on Telecommunications and Signal Processing (TSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.12286","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.12286","pdf_url":"https://arxiv.org/pdf/2009.12286","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":"mag:3088490496","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2009.12286.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2009.12286","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.12286","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.12286","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.12286","pdf_url":"https://arxiv.org/pdf/2009.12286","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3088490496.pdf","grobid_xml":"https://content.openalex.org/works/W3088490496.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1897240248","https://openalex.org/W2069681747","https://openalex.org/W2121973264","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2609317876","https://openalex.org/W2620812332","https://openalex.org/W2734774145","https://openalex.org/W2773624778","https://openalex.org/W2774389566","https://openalex.org/W2797972631","https://openalex.org/W2808920027","https://openalex.org/W2889442120","https://openalex.org/W2890075319","https://openalex.org/W2892110446","https://openalex.org/W2906042495","https://openalex.org/W2908510526","https://openalex.org/W2952218014","https://openalex.org/W2962843322","https://openalex.org/W2962866211","https://openalex.org/W2963189033","https://openalex.org/W2963902628","https://openalex.org/W2964058413","https://openalex.org/W2964199361","https://openalex.org/W2971417062","https://openalex.org/W2972693890","https://openalex.org/W2997901485","https://openalex.org/W2998155746","https://openalex.org/W3010312271","https://openalex.org/W3015679215","https://openalex.org/W3015843733","https://openalex.org/W3016109656","https://openalex.org/W3016120385","https://openalex.org/W3098606562","https://openalex.org/W3123318516","https://openalex.org/W4289665794","https://openalex.org/W6757632829","https://openalex.org/W6757817989"],"related_works":["https://openalex.org/W3191448984","https://openalex.org/W2952218014","https://openalex.org/W1552314771","https://openalex.org/W3160129476","https://openalex.org/W2905116791","https://openalex.org/W3109051940","https://openalex.org/W3170898599","https://openalex.org/W2618428124","https://openalex.org/W3139123974","https://openalex.org/W2988514316","https://openalex.org/W2962710991","https://openalex.org/W2885097243","https://openalex.org/W3169302346","https://openalex.org/W2948695999","https://openalex.org/W2912435603","https://openalex.org/W3013134448","https://openalex.org/W3157912086","https://openalex.org/W3115260384","https://openalex.org/W3205009459","https://openalex.org/W3203678853"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"speech":[2],"enhancement":[3],"for":[4,67],"real-time":[5],"applications":[6],"recently":[7],"made":[8],"large":[9],"advancements.":[10],"Due":[11],"to":[12,30,74,103],"the":[13,28,33,107,123],"lack":[14],"of":[15,32,63],"a":[16,60,68,119],"tractable":[17],"perceptual":[18],"optimization":[19],"target,":[20],"many":[21,37],"myths":[22],"around":[23],"training":[24,53],"losses":[25,134],"emerged,":[26],"whereas":[27],"contribution":[29],"success":[31],"loss":[34,64],"functions":[35,66],"in":[36,76],"cases":[38],"has":[39],"not":[40,110],"been":[41],"investigated":[42],"isolated":[43],"from":[44],"other":[45,124],"factors":[46],"such":[47,135],"as":[48,136],"network":[49,71],"architecture,":[50],"features,":[51],"or":[52],"procedures.":[54],"In":[55],"this":[56],"work,":[57],"we":[58],"investigate":[59],"wide":[61],"variety":[62],"spectral":[65,115],"recurrent":[69],"neural":[70],"architecture":[72],"suitable":[73],"operate":[75],"online":[77],"frame-by-frame":[78],"processing.":[79],"We":[80],"relate":[81],"magnitude-only":[82,97],"with":[83,98],"phase-aware":[84,99],"losses,":[85],"ratios,":[86],"correlation":[87],"metrics,":[88],"and":[89],"compressed":[90,114],"metrics.":[91],"Our":[92],"results":[93],"reveal":[94],"that":[95],"combining":[96],"objectives":[100],"always":[101],"leads":[102],"improvements,":[104],"even":[105],"when":[106],"phase":[108],"is":[109,128],"enhanced.":[111],"Furthermore,":[112],"using":[113],"values":[116],"also":[117],"yields":[118],"significant":[120],"improvement.":[121],"On":[122],"hand,":[125],"phase-sensitive":[126],"improvement":[127],"best":[129],"achieved":[130],"by":[131],"linear":[132],"domain":[133],"mean":[137],"absolute":[138],"error.":[139]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}