{"id":"https://openalex.org/W4319586149","doi":"https://doi.org/10.1109/iscslp57327.2022.10038225","title":"A Speech-Noise-Equilibrium Loss Function for Deep Learning-Based Speech Enhancement","display_name":"A Speech-Noise-Equilibrium Loss Function for Deep Learning-Based Speech Enhancement","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586149","doi":"https://doi.org/10.1109/iscslp57327.2022.10038225"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038225","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5063976041","display_name":"Weitong Zhao","orcid":"https://orcid.org/0000-0003-0996-1206"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitong Zhao","raw_affiliation_strings":["Shenzhen University,The Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering,Shenzhen,Guangdong,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,The Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering,Shenzhen,Guangdong,China,518060","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081605745","display_name":"Fushi Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fushi Xie","raw_affiliation_strings":["Shenzhen University,The Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering,Shenzhen,Guangdong,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,The Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering,Shenzhen,Guangdong,China,518060","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062528115","display_name":"Kang Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Ouyang","raw_affiliation_strings":["Shenzhen University,The Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering,Shenzhen,Guangdong,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,The Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering,Shenzhen,Guangdong,China,518060","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078485183","display_name":"Nengheng Zheng","orcid":"https://orcid.org/0000-0002-4493-1160"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nengheng Zheng","raw_affiliation_strings":["Shenzhen University,The Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering,Shenzhen,Guangdong,China,518060"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University,The Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering,Shenzhen,Guangdong,China,518060","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.3691,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5612708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"468","last_page":"472"},"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":0.9965999722480774,"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":0.9962999820709229,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7616252899169922},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7172055244445801},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6804816722869873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6601580381393433},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.6592168807983398},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.544080913066864},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5126253962516785},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.48733505606651306},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.47892293334007263},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44801822304725647},{"id":"https://openalex.org/keywords/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.4154036343097687},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.37199488282203674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3673921823501587},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3624526858329773},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2593582272529602},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21086785197257996},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12365952134132385},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.11111834645271301}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7616252899169922},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7172055244445801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6804816722869873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6601580381393433},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.6592168807983398},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.544080913066864},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5126253962516785},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.48733505606651306},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.47892293334007263},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44801822304725647},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.4154036343097687},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.37199488282203674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3673921823501587},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3624526858329773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2593582272529602},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21086785197257996},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12365952134132385},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.11111834645271301},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038225","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1968939597","https://openalex.org/W2048510784","https://openalex.org/W2065115983","https://openalex.org/W2069681747","https://openalex.org/W2121973264","https://openalex.org/W2126942983","https://openalex.org/W2128653836","https://openalex.org/W2138037515","https://openalex.org/W2141998673","https://openalex.org/W2145760110","https://openalex.org/W2149535104","https://openalex.org/W2164656607","https://openalex.org/W2168379380","https://openalex.org/W2403117493","https://openalex.org/W2774425939","https://openalex.org/W2799091137","https://openalex.org/W2962866211","https://openalex.org/W2969917057","https://openalex.org/W2971417062","https://openalex.org/W3016255156","https://openalex.org/W3016478097","https://openalex.org/W3103003256","https://openalex.org/W3161525290","https://openalex.org/W4253928870"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2361247493","https://openalex.org/W2157330024","https://openalex.org/W2037635165","https://openalex.org/W3000153094","https://openalex.org/W2542062716","https://openalex.org/W2738829087","https://openalex.org/W2231565466","https://openalex.org/W3043214604","https://openalex.org/W1998374630"],"abstract_inverted_index":{"The":[0],"deep":[1],"learning":[2],"(DL)-based":[3],"speech":[4,60,91,131],"enhancement":[5],"(SE)":[6],"has":[7],"demonstrated":[8],"its":[9],"advantage":[10],"over":[11],"the":[12,20,26,59,63,72,75,79,118,126],"classical":[13],"methods.":[14],"In":[15],"most":[16],"DL-based":[17],"SEs,":[18],"however,":[19],"systems":[21,116],"are":[22],"optimized":[23],"based":[24,70],"on":[25,71],"minimum":[27],"mean":[28,83],"squared":[29],"error":[30,85],"(MSE),":[31],"which":[32],"could":[33],"result":[34],"in":[35,38],"poor":[36],"performance":[37,124],"severe":[39],"noise":[40,64],"conditions,":[41],"e.g.,":[42],"very":[43],"low":[44,136],"signal-to-noise":[45,137],"ratios.":[46,138],"This":[47],"paper":[48],"presents":[49],"a":[50,55,82],"speech-noise-equilibrium":[51],"loss":[52,120],"function,":[53],"i.e.,":[54,96],"weighted":[56],"combination":[57],"of":[58,74,78],"distortion":[61],"and":[62,93,133],"residue,":[65],"for":[66,90,103],"network":[67,104],"training.":[68],"Furthermore,":[69],"observation":[73],"non-Gaussian":[76],"distribution":[77],"prediction":[80],"error,":[81],"absolute":[84],"(MAE)":[86],"criterion":[87],"is":[88,101],"adopted":[89],"distortion,":[92],"hybrid":[94],"training,":[95],"MSE":[97],"followed":[98],"by":[99],"MAE,":[100],"proposed":[102,119],"optimization.":[105],"Experiment":[106],"results":[107],"demonstrate":[108],"that":[109],"long-short":[110],"term":[111],"memory":[112],"networks":[113],"(LSTM)-based":[114],"SE":[115],"with":[117],"function":[121],"achieve":[122],"better":[123],"than":[125],"baselines,":[127],"particularly,":[128],"improving":[129],"both":[130],"quality":[132],"intelligibility":[134],"at":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}