{"id":"https://openalex.org/W3177048943","doi":"https://doi.org/10.1186/s13636-021-00207-6","title":"Components loss for neural networks in mask-based speech enhancement","display_name":"Components loss for neural networks in mask-based speech enhancement","publication_year":2021,"publication_date":"2021-07-02","ids":{"openalex":"https://openalex.org/W3177048943","doi":"https://doi.org/10.1186/s13636-021-00207-6","mag":"3177048943"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-021-00207-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00207-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00207-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00207-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070273121","display_name":"Ziyi Xu","orcid":"https://orcid.org/0000-0003-3046-1425"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ziyi Xu","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Schleinitzstr. 22, Braunschweig, 38106, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3046-1425","affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Schleinitzstr. 22, Braunschweig, 38106, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028198687","display_name":"Samy Elshamy","orcid":"https://orcid.org/0000-0002-7517-019X"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Samy Elshamy","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Schleinitzstr. 22, Braunschweig, 38106, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Schleinitzstr. 22, Braunschweig, 38106, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081973657","display_name":"Ziyue Zhao","orcid":"https://orcid.org/0000-0002-3370-0041"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ziyue Zhao","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Schleinitzstr. 22, Braunschweig, 38106, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Schleinitzstr. 22, Braunschweig, 38106, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002593702","display_name":"Tim Fingscheidt","orcid":"https://orcid.org/0000-0002-8895-5041"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Fingscheidt","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Schleinitzstr. 22, Braunschweig, 38106, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Schleinitzstr. 22, Braunschweig, 38106, Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070273121"],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1266,"currency":"EUR","value_usd":1365},"fwci":1.6701,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83739395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"2021","issue":"1","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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987000226974487,"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/pesq","display_name":"PESQ","score":0.9788495898246765},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7177439332008362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6954325437545776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6864666938781738},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5878594517707825},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4925268590450287},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46435546875},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.45788848400115967},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43389642238616943},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4326073229312897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34940677881240845},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2763425409793854},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20207160711288452},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17327821254730225},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10248121619224548},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09727326035499573}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9788495898246765},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7177439332008362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6954325437545776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6864666938781738},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5878594517707825},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4925268590450287},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46435546875},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.45788848400115967},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43389642238616943},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4326073229312897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34940677881240845},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2763425409793854},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20207160711288452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17327821254730225},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10248121619224548},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09727326035499573},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-021-00207-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00207-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00207-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b16c307ec2d74ac6b4daa7c210ee9e2b","is_oa":true,"landing_page_url":"https://doaj.org/article/b16c307ec2d74ac6b4daa7c210ee9e2b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2021, Iss 1, Pp 1-20 (2021)","raw_type":"article"},{"id":"pmh:oai:publikationsserver.tu-braunschweig.de:dbbs_mods_00070530","is_oa":true,"landing_page_url":"http://publikationsserver.tu-braunschweig.de/get/70530","pdf_url":null,"source":{"id":"https://openalex.org/S4306402617","display_name":"Digitale Bibliothek Braunschweig (Verbundzentrale G\u00f6ttingen (VZG))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210149878","host_organization_name":"Verbundzentrale des GBV","host_organization_lineage":["https://openalex.org/I4210149878"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on audio, speech, and music processing, 2021, 24 (2021). https://doi.org/10.1186/s13636-021-00207-6 -- 1687-4722 -- 1687-4714","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-021-00207-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00207-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00207-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322958","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3177048943.pdf","grobid_xml":"https://content.openalex.org/works/W3177048943.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W104228359","https://openalex.org/W1482149378","https://openalex.org/W1516630152","https://openalex.org/W1552516442","https://openalex.org/W1964509438","https://openalex.org/W1989387577","https://openalex.org/W2015143272","https://openalex.org/W2031647436","https://openalex.org/W2046869671","https://openalex.org/W2067295501","https://openalex.org/W2069486713","https://openalex.org/W2069681747","https://openalex.org/W2115939208","https://openalex.org/W2118354544","https://openalex.org/W2121894251","https://openalex.org/W2121973264","https://openalex.org/W2130476329","https://openalex.org/W2137643203","https://openalex.org/W2145310550","https://openalex.org/W2153022037","https://openalex.org/W2153894152","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2345067732","https://openalex.org/W2407929794","https://openalex.org/W2517760955","https://openalex.org/W2541674938","https://openalex.org/W2612685246","https://openalex.org/W2620812332","https://openalex.org/W2786835328","https://openalex.org/W2805233667","https://openalex.org/W2809824582","https://openalex.org/W2886515811","https://openalex.org/W2889373351","https://openalex.org/W2889890482","https://openalex.org/W2892110446","https://openalex.org/W2892129657","https://openalex.org/W2936709989","https://openalex.org/W2951280222","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963351212","https://openalex.org/W2997901485","https://openalex.org/W2998155746","https://openalex.org/W3003901600","https://openalex.org/W3015844538","https://openalex.org/W3016109656","https://openalex.org/W3016120385","https://openalex.org/W3097312999","https://openalex.org/W3103619082","https://openalex.org/W3147539069","https://openalex.org/W4376532917","https://openalex.org/W6602820859"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"Abstract":[0],"Estimating":[1],"time-frequency":[2],"domain":[3],"masks":[4,218],"for":[5,33,39,90],"single-channel":[6],"speech":[7,41,57,92,112,129,175,180],"enhancement":[8],"using":[9],"deep":[10],"learning":[11],"methods":[12],"has":[13],"recently":[14,142,211],"become":[15],"a":[16,28,68,84,157,162,186,222],"popular":[17],"research":[18],"field":[19],"with":[20,146,216,224],"promising":[21],"results.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,196],"propose":[27],"novel":[29],"components":[30],"loss":[31,110,121,132,145,215],"(CL)":[32],"the":[34,44,47,56,62,76,79,104,125,134,141,153,229,249,258],"training":[35,45],"of":[36,55,61,67,78,128],"neural":[37,87],"networks":[38],"mask-based":[40,91],"enhancement.":[42,93],"During":[43],"process,":[46],"proposed":[48,80,143,154,212,250],"CL":[49,81,96,155,251],"offers":[50],"separate":[51],"control":[52],"over":[53],"preservation":[54,66],"component":[58,176],"quality,":[59,177,181],"suppression":[60],"noise":[63,72,190,194,245],"component,":[64],"and":[65,133,139,182,239,241,270],"naturally":[69],"sounding":[70,188],"residual":[71,189,244],"component.":[73,191],"We":[74],"illustrate":[75],"potential":[77],"by":[82,202],"evaluating":[83],"standard":[85],"convolutional":[86],"network":[88,223],"(CNN)":[89],"The":[94,210],"new":[95],"is":[97,266,272],"compared":[98],"to":[99,228,268],"several":[100],"baseline":[101],"losses,":[102],"comprising":[103],"conventional":[105],"mean":[106],"squared":[107],"error":[108],"(MSE)":[109],"w.r.t.":[111,116,243],"spectral":[113],"amplitudes":[114],"or":[115,159],"an":[117,203],"ideal-ratio":[118],"mask,":[119],"auditory-related":[120],"functions,":[122],"such":[123],"as":[124],"perceptual":[126,135],"evaluation":[127,259],"quality":[130,170],"(PESQ)":[131],"weighting":[136],"filter":[137],"loss,":[138],"also":[140,184,234],"SNR":[144,173,214],"two":[147,217,230],"masks.":[148],"Detailed":[149],"analysis":[150],"suggests":[151],"that":[152,248],"obtains":[156],"better":[158],"at":[160,274],"least":[161],"more":[163,225,254],"balanced":[164],"performance":[165],"across":[166],"all":[167],"employed":[168],"instrumental":[169],"metrics,":[171],"including":[172],"improvement,":[174],"enhanced":[178],"total":[179],"particularly":[183,242],"delivers":[185],"natural":[187],"For":[192],"unseen":[193],"types,":[195],"excel":[197],"even":[198],"perceptually":[199],"motivated":[200],"losses":[201],"about":[204],"0.2":[205],"points":[206],"higher":[207],"PESQ":[208,238],"score.":[209],"so-called":[213],"not":[219],"only":[220],"requires":[221],"parameters":[226],"due":[227],"decoder":[231],"heads,":[232],"but":[233],"falls":[235],"behind":[236],"on":[237],"POLQA":[240],"quality.":[246],"Note":[247],"shows":[252],"significantly":[253],"1st":[255],"ranks":[256],"among":[257],"metrics":[260],"than":[261],"any":[262],"other":[263],"baseline.":[264],"It":[265],"easy":[267],"implement,":[269],"code":[271],"provided":[273],"https://github.com/ifnspaml/Components-Loss":[275],".":[276]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}