{"id":"https://openalex.org/W2972404066","doi":"https://doi.org/10.21437/interspeech.2019-1567","title":"UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-Noise Ratio Condition","display_name":"UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-Noise Ratio Condition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972404066","doi":"https://doi.org/10.21437/interspeech.2019-1567","mag":"2972404066"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1567","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1567","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.15521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102005971","display_name":"Xiang Hao","orcid":"https://orcid.org/0000-0003-4828-3938"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Hao","raw_affiliation_strings":["Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science, Inner Mongolia Univeristy, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science, Inner Mongolia Univeristy, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010464164","display_name":"Xiangdong Su","orcid":"https://orcid.org/0000-0001-8061-1474"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Su","raw_affiliation_strings":["Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science, Inner Mongolia Univeristy, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science, Inner Mongolia Univeristy, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357195","display_name":"Zhiyu Wang","orcid":"https://orcid.org/0000-0002-9152-7929"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Wang","raw_affiliation_strings":["Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science, Inner Mongolia Univeristy, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science, Inner Mongolia Univeristy, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108035744","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0003-0601-3905"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science, Inner Mongolia Univeristy, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science, Inner Mongolia Univeristy, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031037698","display_name":"Batushiren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"- Batushiren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102005971"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1786","last_page":"1790"},"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":0.9937999844551086,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/pesq","display_name":"PESQ","score":0.932425856590271},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8132154941558838},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7744029760360718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6717929840087891},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5689741969108582},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5539292693138123},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5177925825119019},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47188106179237366},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.43699318170547485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4003342390060425},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21229326725006104},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12907472252845764}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.932425856590271},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8132154941558838},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744029760360718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6717929840087891},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5689741969108582},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5539292693138123},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5177925825119019},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47188106179237366},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.43699318170547485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4003342390060425},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21229326725006104},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12907472252845764},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-1567","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1567","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:2010.15521","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15521","pdf_url":"https://arxiv.org/pdf/2010.15521","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.15521","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.15521","pdf_url":"https://arxiv.org/pdf/2010.15521","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":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1610060839","https://openalex.org/W1635512741","https://openalex.org/W1836465849","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1921523184","https://openalex.org/W1969472131","https://openalex.org/W1974387177","https://openalex.org/W2067295501","https://openalex.org/W2099471712","https://openalex.org/W2105768884","https://openalex.org/W2125389028","https://openalex.org/W2412782625","https://openalex.org/W2592939477","https://openalex.org/W2746457594","https://openalex.org/W2774707525","https://openalex.org/W2805288670","https://openalex.org/W2884250895","https://openalex.org/W2889286744","https://openalex.org/W2892356933","https://openalex.org/W2918296821","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2963828919","https://openalex.org/W2963840672","https://openalex.org/W2963909702","https://openalex.org/W2964121744","https://openalex.org/W4251033893","https://openalex.org/W4302765731","https://openalex.org/W4320013936","https://openalex.org/W4393186488"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,26],"at":[2,83],"extremely":[3],"low":[4,84],"signal-to-noise":[5],"ratio":[6],"(SNR)":[7],"condition":[8],"is":[9],"a":[10,23,45,49,63],"very":[11],"challenging":[12],"problem":[13],"and":[14,32,48,67,104,126,133],"rarely":[15],"investigated":[16],"in":[17,55,71],"previous":[18],"works.":[19],"This":[20,41],"paper":[21],"proposes":[22],"robust":[24],"speech":[25,102,137],"approach":[27,42],"(UNetGAN)":[28],"based":[29],"on":[30,90],"U-Net":[31,64],"generative":[33],"adversarial":[34],"learning":[35,110],"to":[36,88],"deal":[37],"with":[38],"this":[39],"problem.":[40],"consists":[43],"of":[44,74,80,136],"generator":[46,60],"network":[47,61],"discriminator":[50],"network,":[51],"which":[52],"operate":[53],"directly":[54],"the":[56,72,78,81,91,101,107],"time":[57],"domain.":[58],"The":[59,94],"adopts":[62],"like":[65],"structure":[66],"employs":[68],"dilated":[69],"convolution":[70],"bottleneck":[73],"it.":[75],"We":[76],"evaluate":[77],"performance":[79],"UNetGAN":[82],"SNR":[85],"conditions":[86],"(up":[87],"-20dB)":[89],"public":[92],"benchmark.":[93],"result":[95],"demonstrates":[96],"that":[97],"it":[98],"significantly":[99],"improves":[100],"quality":[103,138],"substantially":[105],"outperforms":[106],"representative":[108],"deep":[109],"models,":[111],"including":[112],"SEGAN,":[113],"cGAN":[114],"fo":[115],"SE,":[116],"Bidirectional":[117],"LSTM":[118],"using":[119],"phase-sensitive":[120],"spectrum":[121],"approximation":[122],"cost":[123],"function":[124],"(PSA-BLSTM)":[125],"Wave-U-Net":[127],"regarding":[128],"Short-Time":[129],"Objective":[130],"Intelligibility":[131],"(STOI)":[132],"Perceptual":[134],"evaluation":[135],"(PESQ).":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}