{"id":"https://openalex.org/W3015411705","doi":"https://doi.org/10.1109/icassp40776.2020.9054060","title":"CP-GAN: Context Pyramid Generative Adversarial Network for Speech Enhancement","display_name":"CP-GAN: Context Pyramid Generative Adversarial Network for Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015411705","doi":"https://doi.org/10.1109/icassp40776.2020.9054060","mag":"3015411705"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100412456","display_name":"Gang Liu","orcid":"https://orcid.org/0000-0002-6439-3195"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Liu","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089953417","display_name":"Ke Gong","orcid":"https://orcid.org/0000-0002-8036-2348"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Gong","raw_affiliation_strings":["DarkMatter AI Research"],"affiliations":[{"raw_affiliation_string":"DarkMatter AI Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108648345","display_name":"Zhiguang Chen","orcid":"https://orcid.org/0000-0002-5427-1266"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiguang Chen","raw_affiliation_strings":["Sun Yat-sen University"],"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100412456"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":5.0006,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96287031,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6624","last_page":"6628"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9890999794006348,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9884999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.8140726089477539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8078279495239258},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6954675316810608},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.620304524898529},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.615708589553833},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5456765294075012},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5309115648269653},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.517006516456604},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5145744681358337},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5041357278823853},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.46159741282463074},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41128313541412354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4093404710292816},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21318399906158447},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20141229033470154},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.1176430881023407},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08985993266105652},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07417908310890198},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05675768852233887}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8140726089477539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078279495239258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6954675316810608},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.620304524898529},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.615708589553833},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5456765294075012},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5309115648269653},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.517006516456604},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5145744681358337},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5041357278823853},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.46159741282463074},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41128313541412354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4093404710292816},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21318399906158447},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20141229033470154},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.1176430881023407},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08985993266105652},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07417908310890198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05675768852233887},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1983108229","https://openalex.org/W2094721231","https://openalex.org/W2099471712","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2291877678","https://openalex.org/W2565639579","https://openalex.org/W2600628583","https://openalex.org/W2603567530","https://openalex.org/W2621984810","https://openalex.org/W2787069756","https://openalex.org/W2810518847","https://openalex.org/W2916104401","https://openalex.org/W2940177920","https://openalex.org/W2954695182","https://openalex.org/W2963073614","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963446712","https://openalex.org/W2963470893","https://openalex.org/W2964121592","https://openalex.org/W2972425344","https://openalex.org/W2973215447","https://openalex.org/W4320013936","https://openalex.org/W6629717138","https://openalex.org/W6727340567","https://openalex.org/W6735168207"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W111365173","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285"],"abstract_inverted_index":{"The":[0],"topic":[1],"of":[2,14,59,127],"speech":[3,36,77,81,120,130,134],"enhancement":[4,37,82,121],"has":[5],"been":[6],"largely":[7],"improved":[8],"recently,":[9],"especially":[10],"with":[11],"the":[12,24,35,40,57,60,68,73,125],"development":[13],"generative":[15],"adversarial":[16],"networks":[17],"(GANs).":[18],"However":[19],"prior":[20],"methods":[21],"simply":[22],"follow":[23],"GAN":[25],"architectures":[26],"from":[27],"computer":[28],"vision":[29],"tasks":[30,131],"without":[31],"specific":[32],"designs":[33],"for":[34,79],"according":[38],"to":[39,71,105],"audio":[41,108],"characteristics":[42],"(i.e.,":[43],"different":[44],"granularity":[45,103],"context),":[46],"which":[47,92],"may":[48],"leave":[49],"noise":[50,109],"points":[51],"in":[52],"some":[53],"segments":[54],"or":[55],"disturb":[56],"contents":[58],"original":[61],"audio.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"make":[67],"first":[69],"attempt":[70],"explore":[72],"global":[74],"and":[75,83,99,123,136],"local":[76],"features":[78],"coarse-to-fine":[80],"introduce":[84],"a":[85,94,100],"Context":[86],"Pyramid":[87],"Generative":[88],"Adversarial":[89],"Network":[90],"(CPGAN),":[91],"contains":[93],"densely-connected":[95],"feature":[96],"pyramid":[97],"generator":[98],"dynamic":[101],"context":[102],"discriminator":[104],"better":[106],"eliminate":[107],"hierarchically.":[110],"Extensive":[111],"experiments":[112],"demonstrate":[113],"that":[114],"our":[115],"CP-GAN":[116],"effectively":[117],"achieves":[118],"state-of-the-art":[119],"results":[122],"boosts":[124],"performance":[126],"more":[128],"high-level":[129],"including":[132],"automatic":[133],"recognition":[135],"speaker":[137],"recognition.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}