{"id":"https://openalex.org/W4392931778","doi":"https://doi.org/10.1109/icassp48485.2024.10448333","title":"Employing Real Training Data for Deep Noise Suppression","display_name":"Employing Real Training Data for Deep Noise Suppression","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931778","doi":"https://doi.org/10.1109/icassp48485.2024.10448333"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448333","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":false,"raw_author_name":"Ziyi Xu","raw_affiliation_strings":["Technische Universität Braunschweig,Institute for Communications Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Braunschweig,Institute for Communications Technology,Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110895535","display_name":"Marvin Sach","orcid":null},"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":"Marvin Sach","raw_affiliation_strings":["Technische Universität Braunschweig,Institute for Communications Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Braunschweig,Institute for Communications Technology,Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071371030","display_name":"Jan Pirklbauer","orcid":"https://orcid.org/0009-0004-5882-4317"},"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":"Jan Pirklbauer","raw_affiliation_strings":["Technische Universität Braunschweig,Institute for Communications Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Braunschweig,Institute for Communications Technology,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":["Technische Universität Braunschweig,Institute for Communications Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Braunschweig,Institute for Communications Technology,Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"133","issue":null,"first_page":"10731","last_page":"10735"},"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":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.98831707239151},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8074520230293274},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5953698754310608},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4969225227832794},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4836372137069702},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4681167006492615},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4542364478111267},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.441830575466156},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3623107969760895},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3365124464035034},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22442010045051575}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.98831707239151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8074520230293274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5953698754310608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4969225227832794},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4836372137069702},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4681167006492615},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4542364478111267},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.441830575466156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3623107969760895},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3365124464035034},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22442010045051575},{"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448333","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448333","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1506438021","https://openalex.org/W1983108229","https://openalex.org/W2067295501","https://openalex.org/W2125114513","https://openalex.org/W2892356933","https://openalex.org/W2940275453","https://openalex.org/W2962866211","https://openalex.org/W2963341071","https://openalex.org/W2998155746","https://openalex.org/W3015844538","https://openalex.org/W3092864146","https://openalex.org/W3097312999","https://openalex.org/W3097906045","https://openalex.org/W3161480375","https://openalex.org/W3163464523","https://openalex.org/W3191448984","https://openalex.org/W3196475561","https://openalex.org/W3197042120","https://openalex.org/W3198130028","https://openalex.org/W3212906118","https://openalex.org/W4225302959","https://openalex.org/W4253928870","https://openalex.org/W4312877393","https://openalex.org/W4320013820","https://openalex.org/W4386902723","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"Most":[0],"deep":[1,78],"noise":[2],"suppression":[3],"(DNS)":[4],"models":[5,39],"are":[6],"trained":[7,139],"with":[8,140],"reference-based":[9],"losses":[10],"requiring":[11],"access":[12,62],"to":[13,29,41,63,73,84],"clean":[14,66],"speech.":[15,67],"However,":[16],"sometimes":[17],"an":[18,75,117],"additive":[19],"microphone":[20],"model":[21,125,138],"is":[22],"insufficient":[23],"for":[24,37,50,103,196],"real-world":[25],"applications.":[26],"Accordingly,":[27],"ways":[28],"use":[30,116],"real":[31,48,95,105,127,144,179],"training":[32,52,120,153],"data":[33,49,106,145],"in":[34],"supervised":[35],"learning":[36],"DNS":[38,51,108,124,137,166],"promise":[40],"reduce":[42],"a":[43,58,99,170,197],"potential":[44],"training/inference":[45],"mismatch.":[46],"Employing":[47],"requires":[53],"either":[54],"generative":[55],"approaches":[56],"or":[57],"reference-free":[59,100],"loss":[60,102],"without":[61],"the":[64,111,123,141,163,182,186],"corresponding":[65],"In":[68],"this":[69],"work,":[70],"we":[71,115],"propose":[72],"employ":[74],"end-to-end":[76],"non-intrusive":[77],"neural":[79],"network":[80],"(DNN),":[81],"named":[82],"PESQ-DNN,":[83],"estimate":[85],"perceptual":[86,101,199],"evaluation":[87],"of":[88,93],"speech":[89],"quality":[90],"(PESQ)":[91],"scores":[92],"enhanced":[94],"data.":[96,135,154],"It":[97],"provides":[98],"employing":[104,143,150],"during":[107],"training,":[109],"maximizing":[110],"PESQ":[112,173],"scores.":[113],"Furthermore,":[114],"epoch-wise":[118],"alternating":[119],"protocol,":[121],"updating":[122,132],"on":[126,133,176],"data,":[128,158,181],"followed":[129],"by":[130,169,188],"PESQ-DNN":[131,142,194],"synthetic":[134,152,156,177],"The":[136],"outperforms":[146],"all":[147],"reference":[148],"methods":[149],"only":[151],"On":[155],"test":[157,180],"our":[159],"proposed":[160,183],"method":[161,184],"excels":[162],"Inter-speech":[164],"2021":[165],"Challenge":[167],"baseline":[168,187],"significant":[171],"0.32":[172],"points.":[174],"Both":[175],"and":[178],"beats":[185],"0.05":[189],"DNSMOS":[190],"points":[191],"\u2013":[192],"although":[193],"optimizes":[195],"different":[198],"metric.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}