{"id":"https://openalex.org/W2746457594","doi":"https://doi.org/10.21437/interspeech.2017-1620","title":"Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification","display_name":"Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2746457594","doi":"https://doi.org/10.21437/interspeech.2017-1620","mag":"2746457594"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1620","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1709.01703","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063187524","display_name":"Daniel Michelsanti","orcid":"https://orcid.org/0000-0002-3575-1600"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Daniel Michelsanti","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Denmark"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063187524"],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":27.5505,"has_fulltext":true,"cited_by_count":253,"citation_normalized_percentile":{"value":0.99802345,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2008","last_page":"2012"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/spectrogram","display_name":"Spectrogram","score":0.890615701675415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7752193212509155},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.763007402420044},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7198523879051208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7132861018180847},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5992529392242432},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5442233085632324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.487984836101532},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45804351568222046},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4570707082748413},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4557811915874481},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4205721616744995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3992355465888977},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.27474379539489746},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24066948890686035},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.0833059549331665}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.890615701675415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752193212509155},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.763007402420044},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7198523879051208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7132861018180847},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5992529392242432},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5442233085632324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.487984836101532},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45804351568222046},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4570707082748413},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4557811915874481},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4205721616744995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3992355465888977},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27474379539489746},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24066948890686035},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0833059549331665},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-1620","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1709.01703","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.01703","pdf_url":"https://arxiv.org/pdf/1709.01703","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":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:openaire/2f09b76f-10ee-4612-866e-9b9b24e282de","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/2f09b76f-10ee-4612-866e-9b9b24e282de","pdf_url":"https://arxiv.org/pdf/1709.01703.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"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":"Michelsanti, D & Tan, Z-H 2017, Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification. in Proc. Interspeech 2017. ISCA, INTERSPEECH , pp. 2008-2012, Interspeech 2017, Stockholm, Sweden, 20/08/2017. https://doi.org/10.21437/Interspeech.2017-1620","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1709.01703","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1709.01703","pdf_url":"https://arxiv.org/pdf/1709.01703","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G1122009699","display_name":null,"funder_award_id":"647850","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6604660569","display_name":null,"funder_award_id":"1335-00162","funder_id":"https://openalex.org/F4320322928","funder_display_name":"Danmarks Frie Forskningsfond"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322928","display_name":"Danmarks Frie Forskningsfond","ror":"https://ror.org/02sptwz63"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W1996512145","https://openalex.org/W2044893557","https://openalex.org/W2062164080","https://openalex.org/W2069681747","https://openalex.org/W2121973264","https://openalex.org/W2123045220","https://openalex.org/W2125389028","https://openalex.org/W2131753991","https://openalex.org/W2141998673","https://openalex.org/W2173520492","https://openalex.org/W2184218725","https://openalex.org/W2298992465","https://openalex.org/W2342877626","https://openalex.org/W2364134690","https://openalex.org/W2405774341","https://openalex.org/W2510625446","https://openalex.org/W2523714292","https://openalex.org/W2526733715","https://openalex.org/W2544164552","https://openalex.org/W2550397165","https://openalex.org/W2552465644","https://openalex.org/W2559110679","https://openalex.org/W2561557072","https://openalex.org/W2577946330","https://openalex.org/W2580458810","https://openalex.org/W2586068394","https://openalex.org/W2949117887","https://openalex.org/W2962914040","https://openalex.org/W2963017889","https://openalex.org/W2963073614","https://openalex.org/W2963420272","https://openalex.org/W2963453742","https://openalex.org/W2963470893","https://openalex.org/W2963684088","https://openalex.org/W3147539069","https://openalex.org/W4320013936"],"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":{"Improving":[0],"speech":[1,12,77,143],"system":[2],"performance":[3,132],"in":[4,34,52,89,137],"noisy":[5,76,101,125],"environments":[6],"remains":[7],"a":[8,35,70,93,104,128,185],"challenging":[9],"task,":[10],"and":[11,51,103,117,150,181],"enhancement":[13],"(SE)":[14],"is":[15,182],"one":[16],"of":[17,29,37,45,57,75,85,133,139,142,155],"the":[18,23,26,43,58,73,99,115,121,124,131,134,164,169],"effective":[19],"techniques":[20],"to":[21,68,78,97,108,184],"solve":[22],"problem.Motivated":[24],"by":[25,63,114],"promising":[27],"results":[28,161],"generative":[30],"adversarial":[31,91],"networks":[32],"(GANs)":[33],"variety":[36],"image":[38,59],"processing":[39,60],"tasks,":[40],"we":[41,54],"explore":[42],"potential":[44],"conditional":[46],"GANs":[47],"(cGANs)":[48],"for":[49],"SE,":[50],"particular,":[53],"make":[55],"use":[56],"framework":[61],"proposed":[62],"Isola":[64],"et":[65],"al.":[66],"[1]":[67],"learn":[69],"mapping":[71],"from":[72,120],"spectrogram":[74,126],"an":[79,90],"enhanced":[80,111],"counterpart.The":[81],"SE":[82,179,189],"cGAN":[83,135,165],"consists":[84],"two":[86],"networks,":[87],"trained":[88],"manner:":[92],"generator":[94,116],"that":[95,106,163],"tries":[96,107],"enhance":[98],"input":[100],"spectrogram,":[102],"discriminator":[105],"distinguish":[109],"between":[110],"spectrograms":[112],"provided":[113],"clean":[118],"ones":[119],"database":[122],"using":[123],"as":[127],"condition.We":[129],"evaluate":[130],"method":[136,166],"terms":[138],"perceptual":[140],"evaluation":[141],"quality":[144],"(PESQ),":[145],"short-time":[146,171],"objective":[147],"intelligibility":[148],"(STOI),":[149],"equal":[151],"error":[152,177],"rate":[153],"(EER)":[154],"speaker":[156],"verification":[157],"(an":[158],"example":[159],"application).Experimental":[160],"show":[162],"overall":[167],"outperforms":[168],"classical":[170],"spectral":[172],"amplitude":[173],"minimum":[174],"mean":[175],"square":[176],"(STSA-MMSE)":[178],"algorithm,":[180],"comparable":[183],"deep":[186],"neural":[187],"network-based":[188],"approach":[190],"(DNN-SE).":[191]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":40},{"year":2020,"cited_by_count":64},{"year":2019,"cited_by_count":48},{"year":2018,"cited_by_count":31},{"year":2017,"cited_by_count":4}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}