{"id":"https://openalex.org/W3016109656","doi":"https://doi.org/10.1109/icassp40776.2020.9052968","title":"Using Separate Losses for Speech and Noise in Mask-Based Speech Enhancement","display_name":"Using Separate Losses for Speech and Noise in Mask-Based Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016109656","doi":"https://doi.org/10.1109/icassp40776.2020.9052968","mag":"3016109656"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052968","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":["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/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, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t, Braunschweig, 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, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t, Braunschweig, 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, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070273121"],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":null,"apc_paid":null,"fwci":1.8184,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.85457538,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7519","last_page":"7523"},"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":0.9993000030517578,"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":0.9986000061035156,"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/pesq","display_name":"PESQ","score":0.9871891140937805},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8747515678405762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7413943409919739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.719542384147644},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5403333902359009},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4941242039203644},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48434364795684814},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4746820628643036},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4199438989162445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3663650155067444},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.35921990871429443},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1422698199748993},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12478306889533997},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07122993469238281}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9871891140937805},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8747515678405762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7413943409919739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719542384147644},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5403333902359009},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4941242039203644},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48434364795684814},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4746820628643036},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4199438989162445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3663650155067444},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.35921990871429443},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1422698199748993},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12478306889533997},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07122993469238281},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052968","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W104228359","https://openalex.org/W1482149378","https://openalex.org/W1516630152","https://openalex.org/W1989387577","https://openalex.org/W2015143272","https://openalex.org/W2046869671","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2116881528","https://openalex.org/W2118354544","https://openalex.org/W2121894251","https://openalex.org/W2121973264","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/W2612685246","https://openalex.org/W2620812332","https://openalex.org/W2786835328","https://openalex.org/W2809824582","https://openalex.org/W2892110446","https://openalex.org/W2963351212","https://openalex.org/W3147539069","https://openalex.org/W6604196810","https://openalex.org/W6668037159","https://openalex.org/W6713778657","https://openalex.org/W6995365356"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","https://openalex.org/W1973895194","https://openalex.org/W3135613579","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":{"Estimating":[0],"time-frequency":[1],"domain":[2],"masks":[3],"for":[4,29,35,76],"speech":[5,36,58,78,108,132,154],"enhancement":[6],"using":[7],"deep":[8],"learning":[9],"approaches":[10],"has":[11],"recently":[12],"become":[13],"a":[14,24,71,140,147],"popular":[15],"field":[16],"in":[17,83],"research.":[18],"In":[19,136],"this":[20],"paper,":[21],"we":[22],"propose":[23],"novel":[25],"components":[26],"loss":[27,102],"(CL)":[28],"the":[30,39,42,51,57,62,65,91,96,131,152],"training":[31,40],"of":[32,50,56,64,70,107],"neural":[33,73],"networks":[34],"enhancement.":[37,79],"During":[38],"process,":[41],"proposed":[43,66],"CL":[44,67],"offers":[45],"separate":[46],"control":[47],"over":[48,90],"suppression":[49],"noise":[52,145],"component":[53,133],"and":[54,103,121,146],"preservation":[55],"component.":[59],"We":[60,80],"illustrate":[61],"potential":[63],"by":[68],"example":[69],"convolutional":[72],"network":[74],"(CNN)":[75],"mask-based":[77],"show":[81],"improvement":[82,120],"almost":[84],"all":[85],"employed":[86],"instrumental":[87],"quality":[88,109],"metrics":[89],"baseline":[92],"losses,":[93],"which":[94],"comprises":[95],"conventional":[97],"mean":[98],"squared":[99],"error":[100],"(MSE)":[101],"also":[104],"perceptual":[105],"evaluation":[106],"(PESQ)":[110],"loss.":[111],"On":[112],"average,":[113],"more":[114,141,160],"than":[115],"0.3":[116],"dB":[117],"higher":[118,127],"SNR":[119,164],"an":[122],"at":[123,162],"least":[124],"0.1":[125],"points":[126],"PESQ":[128,150],"score":[129],"on":[130,151],"are":[134,159],"obtained.":[135,156],"addition":[137],"to":[138],"that,":[139],"naturally":[142],"sounding":[143],"residual":[144],"consistently":[148],"best":[149],"enhanced":[153],"is":[155],"All":[157],"improvements":[158],"distinct":[161],"low":[163],"conditions.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}