{"id":"https://openalex.org/W2810843531","doi":"https://doi.org/10.21437/interspeech.2019-1924","title":"Speech Denoising with Deep Feature Losses","display_name":"Speech Denoising with Deep Feature Losses","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2810843531","doi":"https://doi.org/10.21437/interspeech.2019-1924","mag":"2810843531"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1924","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.10522","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102812631","display_name":"Fran\u00e7ois G. Germain","orcid":"https://orcid.org/0000-0002-8973-5315"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois G. Germain","raw_affiliation_strings":["Intel (United States), Santa Clara, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel (United States), Santa Clara, United States","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719529","display_name":"Qifeng Chen","orcid":"https://orcid.org/0000-0003-2199-3948"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qifeng Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006181255","display_name":"Vladlen Koltun","orcid":"https://orcid.org/0000-0003-0858-0970"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladlen Koltun","raw_affiliation_strings":["Intel (United States), Santa Clara, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel (United States), Santa Clara, United States","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.84,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95915759,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2723","last_page":"2727"},"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":0.9976000189781189,"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":0.80174720287323},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6291419863700867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6277430653572083},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6239845752716064},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5860995650291443},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5604892373085022},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5357922911643982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5176311135292053},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4989638328552246},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.46598854660987854},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.46106085181236267},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3859517574310303},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07353833317756653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80174720287323},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6291419863700867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6277430653572083},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6239845752716064},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5860995650291443},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5604892373085022},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5357922911643982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5176311135292053},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4989638328552246},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.46598854660987854},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.46106085181236267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3859517574310303},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07353833317756653},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2019-1924","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1806.10522","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.10522","pdf_url":"https://arxiv.org/pdf/1806.10522","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2810843531","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1806.10522","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-98723","is_oa":false,"landing_page_url":"http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=000831796402177","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"pmh:oai:repository.ust.hk:1783.1-98723","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-98723","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"},{"id":"doi:10.48550/arxiv.1806.10522","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1806.10522","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.10522","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.10522","pdf_url":"https://arxiv.org/pdf/1806.10522","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2810843531.pdf","grobid_xml":"https://content.openalex.org/works/W2810843531.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1516630152","https://openalex.org/W1533861849","https://openalex.org/W1546892833","https://openalex.org/W1836465849","https://openalex.org/W1970308149","https://openalex.org/W2013419672","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2095072097","https://openalex.org/W2117539524","https://openalex.org/W2130813098","https://openalex.org/W2138939691","https://openalex.org/W2141411743","https://openalex.org/W2162514423","https://openalex.org/W2176625348","https://openalex.org/W2304609584","https://openalex.org/W2394461504","https://openalex.org/W2405774341","https://openalex.org/W2408467190","https://openalex.org/W2566935005","https://openalex.org/W2594809597","https://openalex.org/W2609317876","https://openalex.org/W2678916739","https://openalex.org/W2747161606","https://openalex.org/W2775302872","https://openalex.org/W2775794021","https://openalex.org/W2949382160","https://openalex.org/W2962785568","https://openalex.org/W2962835968","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963522749","https://openalex.org/W2963840672","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2972443522","https://openalex.org/W2963103134","https://openalex.org/W2600556233","https://openalex.org/W2144404214","https://openalex.org/W2603567530","https://openalex.org/W2962866211","https://openalex.org/W2802304149","https://openalex.org/W2141998673","https://openalex.org/W2949382160","https://openalex.org/W2099471712","https://openalex.org/W2044893557","https://openalex.org/W1983108229","https://openalex.org/W2940177920","https://openalex.org/W2746457594","https://openalex.org/W1897240248","https://openalex.org/W1552314771","https://openalex.org/W1522301498","https://openalex.org/W2981283774","https://openalex.org/W3149225678","https://openalex.org/W3088159194"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2,24,114],"end-to-end":[3],"deep":[4,50,67],"learning":[5],"approach":[6,94,127],"to":[7,31,58],"denoising":[8,143],"speech":[9,21,40,100],"signals":[10],"by":[11,23],"processing":[12],"the":[13,28,39,76,96,125,132,136],"raw":[14],"waveform":[15],"directly.":[16],"Given":[17],"input":[18],"audio":[19,91],"containing":[20],"corrupted":[22],"additive":[25],"background":[26,139],"signal,":[27],"system":[29],"aims":[30],"produce":[32],"a":[33,60,66,81],"processed":[34],"signal":[35],"that":[36],"contains":[37],"only":[38],"content.":[41],"Recent":[42],"approaches":[43],"have":[44],"shown":[45],"promising":[46],"results":[47],"using":[48,65,118],"various":[49],"network":[51,64,116],"architectures.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"propose":[57],"train":[59],"fully-convolutional":[61],"context":[62],"aggregation":[63],"feature":[68,78],"loss.":[69],"That":[70],"loss":[71],"is":[72,128,144],"based":[73],"on":[74],"comparing":[75],"internal":[77],"activations":[79],"in":[80,98,104],"different":[82],"network,":[83],"trained":[84,117],"for":[85,131,141],"acoustic":[86],"environment":[87],"detection":[88],"and":[89,103,147],"domestic":[90],"tagging.":[92],"Our":[93],"outperforms":[95,113],"state-of-the-art":[97],"objective":[99],"quality":[101],"metrics":[102],"large-scale":[105],"perceptual":[106],"experiments":[107],"with":[108,135],"human":[109],"listeners.":[110],"It":[111],"also":[112],"identical":[115],"traditional":[119],"regression":[120],"losses.":[121],"The":[122],"advantage":[123],"of":[124],"new":[126],"particularly":[129],"pronounced":[130],"hardest":[133],"data":[134],"most":[137,145,148],"intrusive":[138],"noise,":[140],"which":[142],"needed":[146],"challenging.":[149]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}