{"id":"https://openalex.org/W2654729393","doi":"https://doi.org/10.1109/icassp.2018.8462417","title":"A Wavenet for Speech Denoising","display_name":"A Wavenet for Speech Denoising","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2654729393","doi":"https://doi.org/10.1109/icassp.2018.8462417","mag":"2654729393"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/1706.07162","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033884279","display_name":"Dario Rethage","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Dario Rethage","raw_affiliation_strings":["Music Technology Group, Universitat pompeu Fabra, Barcelona","Music Technol. Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technol. Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137809","display_name":"Jordi Pons","orcid":"https://orcid.org/0000-0001-9603-0869"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":["Music Technology Group, Universitat pompeu Fabra, Barcelona","Music Technol. Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technol. Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Music Technology Group, Universitat pompeu Fabra, Barcelona","Music Technol. Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technol. Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":2.5251,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.90673509,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5069","last_page":"5073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/spectrogram","display_name":"Spectrogram","score":0.7785093784332275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7056030035018921},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6450403928756714},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6025606989860535},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5668792724609375},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5050542950630188},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49033021926879883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4871077537536621},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.45060113072395325},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.41883039474487305},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41605573892593384},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3699570596218109},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.209201842546463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16244721412658691}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7785093784332275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056030035018921},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6450403928756714},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6025606989860535},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5668792724609375},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5050542950630188},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49033021926879883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4871077537536621},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.45060113072395325},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.41883039474487305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41605573892593384},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3699570596218109},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.209201842546463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16244721412658691},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2018.8462417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1706.07162","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.07162","pdf_url":"https://arxiv.org/pdf/1706.07162","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null},{"id":"pmh:oai:repositori.upf.edu:10230/35669","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/35669","pdf_url":"https://repositori.upf.edu/bitstreams/3efdb20c-be71-47be-a774-2526d49c6dcd/download","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:2654729393","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1706.07162","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.1706.07162","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1706.07162","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1706.07162","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1706.07162","pdf_url":"https://arxiv.org/pdf/1706.07162","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1897240248","https://openalex.org/W1952824372","https://openalex.org/W1983108229","https://openalex.org/W2044893557","https://openalex.org/W2059652044","https://openalex.org/W2094721231","https://openalex.org/W2097117768","https://openalex.org/W2105393299","https://openalex.org/W2112728813","https://openalex.org/W2133340843","https://openalex.org/W2153894152","https://openalex.org/W2168249605","https://openalex.org/W2194775991","https://openalex.org/W2331927446","https://openalex.org/W2394461504","https://openalex.org/W2405774341","https://openalex.org/W2423557781","https://openalex.org/W2520160253","https://openalex.org/W2563637302","https://openalex.org/W2564591810","https://openalex.org/W2587994092","https://openalex.org/W2593179621","https://openalex.org/W2603567530","https://openalex.org/W2611160234","https://openalex.org/W2614024025","https://openalex.org/W2747161606","https://openalex.org/W2949382160","https://openalex.org/W2949937978","https://openalex.org/W2951535099","https://openalex.org/W2953318193","https://openalex.org/W2953331651","https://openalex.org/W2963341071","https://openalex.org/W2963840672","https://openalex.org/W3105202226","https://openalex.org/W4253928870","https://openalex.org/W6673959882","https://openalex.org/W6675274519","https://openalex.org/W6679850134","https://openalex.org/W6682371319","https://openalex.org/W6687566353","https://openalex.org/W6713658392"],"related_works":["https://openalex.org/W2963103134","https://openalex.org/W2949382160","https://openalex.org/W2044893557","https://openalex.org/W2600556233","https://openalex.org/W2747161606","https://openalex.org/W2405774341","https://openalex.org/W2121973264","https://openalex.org/W1522301498","https://openalex.org/W1495679096","https://openalex.org/W1482149378","https://openalex.org/W2928550135","https://openalex.org/W2938908509","https://openalex.org/W2949117887","https://openalex.org/W2078528584","https://openalex.org/W2070126272","https://openalex.org/W1897240248","https://openalex.org/W3024721188","https://openalex.org/W2994785103","https://openalex.org/W3199713199","https://openalex.org/W3164680725"],"abstract_inverted_index":{"Most":[0],"speech":[1,34],"processing":[2,128],"techniques":[3],"use":[4,63],"magnitude":[5,130],"spectrograms":[6],"as":[7],"front-end":[8],"and":[9,68,106,110],"are":[10],"therefore":[11],"by":[12,54],"default":[13],"discarding":[14],"part":[15],"of":[16,64,73,81],"the":[17,19,60,82,99,115,129],"signal:":[18],"phase.":[20],"In":[21],"order":[22],"to":[23],"overcome":[24],"this":[25],"limitation'":[26],"we":[27,84],"propose":[28],"an":[29],"end-to-end":[30],"learning":[31],"method":[32,117,125],"for":[33],"denoising":[35],"based":[36,126],"on":[37,127],"Wavenet.":[38],"The":[39,78],"proposed":[40,116],"model":[41,61,83,100],"adaptation":[42,80],"retains":[43],"Wavenet's":[44],"powerful":[45],"acoustic":[46],"modeling":[47],"capabilities,":[48],"while":[49],"significantly":[50],"reducing":[51],"its":[52,56],"time-complexity":[53],"eliminating":[55],"autoregressive":[57],"nature.":[58],"Specifically,":[59],"makes":[62],"non-causal,":[65],"dilated":[66],"convolutions":[67],"predicts":[69],"target":[70,76],"fields":[71],"instead":[72],"a":[74,88,93,123],"single":[75],"sample.":[77],"discriminative":[79],"propose,":[85],"learns":[86],"in":[87],"supervised":[89],"fashion":[90],"via":[91],"minimizing":[92],"regression":[94],"loss.":[95],"These":[96],"modifications":[97],"make":[98],"highly":[101],"parallelizable":[102],"during":[103],"both":[104],"training":[105],"inference.":[107],"Both":[108],"quantitative":[109],"qualitative":[111],"evaluations":[112],"indicate":[113],"that":[114],"is":[118],"preferred":[119],"over":[120],"Wiener":[121],"filtering,":[122],"common":[124],"spectrogram.":[131]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":4}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}