{"id":"https://openalex.org/W3093911486","doi":"https://doi.org/10.1109/icassp39728.2021.9413555","title":"Perceptual Loss Based Speech Denoising with an Ensemble of Audio Pattern Recognition and Self-Supervised Models","display_name":"Perceptual Loss Based Speech Denoising with an Ensemble of Audio Pattern Recognition and Self-Supervised Models","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3093911486","doi":"https://doi.org/10.1109/icassp39728.2021.9413555","mag":"3093911486"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.11860","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014918159","display_name":"Saurabh Kataria","orcid":"https://orcid.org/0000-0001-6311-2155"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Kataria","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Human Language Technology Center of Excellence,Baltimore,MD","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Human Language Technology Center of Excellence,Baltimore,MD","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesus Villalba","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Human Language Technology Center of Excellence,Baltimore,MD","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Human Language Technology Center of Excellence,Baltimore,MD","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Human Language Technology Center of Excellence,Baltimore,MD","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Human Language Technology Center of Excellence,Baltimore,MD","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7118","last_page":"7122"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7293081879615784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6065480709075928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.520744800567627},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.503929078578949},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4228094816207886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40345093607902527},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33144238591194153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293081879615784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6065480709075928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520744800567627},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.503929078578949},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4228094816207886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40345093607902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33144238591194153}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413555","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.11860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11860","pdf_url":"https://arxiv.org/pdf/2010.11860","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2010.11860","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.11860","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":"Preprint"},{"id":"doi:10.17023/c9m4-fg19","is_oa":true,"landing_page_url":"https://doi.org/10.17023/c9m4-fg19","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"},{"id":"mag:3093911486","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.11860","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11860","pdf_url":"https://arxiv.org/pdf/2010.11860","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093911486.pdf","grobid_xml":"https://content.openalex.org/works/W3093911486.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2193413348","https://openalex.org/W2593116425","https://openalex.org/W2603567530","https://openalex.org/W2810843531","https://openalex.org/W2889462515","https://openalex.org/W2892110446","https://openalex.org/W2902347140","https://openalex.org/W2936774411","https://openalex.org/W2963420686","https://openalex.org/W2963430933","https://openalex.org/W2963677766","https://openalex.org/W2964052309","https://openalex.org/W2994728585","https://openalex.org/W3004253052","https://openalex.org/W3014134198","https://openalex.org/W3015213852","https://openalex.org/W3015219411","https://openalex.org/W3016129867","https://openalex.org/W3024301174","https://openalex.org/W3025165719","https://openalex.org/W3034771406","https://openalex.org/W3036367741","https://openalex.org/W3036601975","https://openalex.org/W3090098535","https://openalex.org/W3096084197","https://openalex.org/W3096159803","https://openalex.org/W3097934054","https://openalex.org/W3097945073","https://openalex.org/W3099782249","https://openalex.org/W3120612350","https://openalex.org/W3163113319","https://openalex.org/W6687566353","https://openalex.org/W6738279954","https://openalex.org/W6743731764","https://openalex.org/W6753100508","https://openalex.org/W6756732229","https://openalex.org/W6771438384","https://openalex.org/W6777337586","https://openalex.org/W6780218876","https://openalex.org/W6782089494"],"related_works":["https://openalex.org/W3163827866","https://openalex.org/W3014973941","https://openalex.org/W3002741552","https://openalex.org/W2972443522","https://openalex.org/W2941290535","https://openalex.org/W2963954250","https://openalex.org/W3041561163","https://openalex.org/W2994785103","https://openalex.org/W2565624985","https://openalex.org/W3088159194","https://openalex.org/W3126699312","https://openalex.org/W3011500442","https://openalex.org/W3031135612","https://openalex.org/W3205533980","https://openalex.org/W3163521645","https://openalex.org/W2963701934","https://openalex.org/W2948661109","https://openalex.org/W2737108017","https://openalex.org/W2787133659","https://openalex.org/W2910254446"],"abstract_inverted_index":{"Deep":[0],"learning":[1,160],"based":[2],"speech":[3,41,63],"denoising":[4,128],"still":[5],"suffers":[6,143],"from":[7,144],"the":[8,30,81,145],"challenge":[9],"of":[10,14,32,147,170,176],"improving":[11],"perceptual":[12,33,123],"quality":[13],"enhanced":[15],"signals.":[16],"We":[17,68],"introduce":[18],"a":[19,71,92,153],"generalized":[20],"framework":[21],"called":[22,85],"Perceptual":[23,35],"Ensemble":[24],"Regularization":[25],"Loss":[26],"(PERL)":[27],"built":[28],"on":[29,80,121],"idea":[31],"losses.":[34,177],"loss":[36],"discourages":[37],"distortion":[38],"to":[39,102,117,168],"certain":[40],"properties":[42],"and":[43,60,98,173],"we":[44,94,133,151],"analyze":[45],"it":[46],"using":[47,76],"six":[48],"large-scale":[49],"pre-trained":[50],"models:":[51],"speaker":[52,56],"classification,":[53,59],"acoustic":[54,96,112],"model,":[55],"embedding,":[57],"emotion":[58],"two":[61],"self-supervised":[62,99],"encoders":[64],"(PASE+,":[65],"wav2vec":[66],"2.0).":[67],"first":[69],"build":[70],"strong":[72],"baseline":[73],"(w/o":[74],"PERL)":[75],"Conformer":[77],"Transformer":[78],"Networks":[79],"popular":[82],"enhancement":[83],"benchmark":[84],"VCTK-DEMAND.":[86],"Using":[87],"auxiliary":[88],"models":[89],"one":[90],"at":[91],"time,":[93],"find":[95,138],"event":[97,113],"model":[100,108,114],"PASE+":[101],"be":[103],"most":[104],"effective.":[105],"Our":[106],"best":[107],"(PERL-AE)":[109],"only":[110],"uses":[111],"(utilizing":[115],"AudioSet)":[116],"outperform":[118,163],"state-of-the-art":[119,157],"methods":[120,161],"major":[122],"metrics.":[124],"To":[125],"explore":[126],"if":[127],"can":[129],"leverage":[130],"full":[131],"framework,":[132],"use":[134],"all":[135],"networks":[136],"but":[137],"that":[139,156],"our":[140],"seven-loss":[141],"formulation":[142],"challenges":[146,169],"Multi-Task":[148,158],"Learning.":[149],"Finally,":[150],"report":[152],"critical":[154],"observation":[155],"weight":[159],"cannot":[162],"hand":[164],"tuning,":[165],"perhaps":[166],"due":[167],"domain":[171],"mismatch":[172],"weak":[174],"complementarity":[175]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}