{"id":"https://openalex.org/W3015910825","doi":"https://doi.org/10.1109/icassp40776.2020.9054256","title":"PAGAN: A Phase-Adapted Generative Adversarial Networks for Speech Enhancement","display_name":"PAGAN: A Phase-Adapted Generative Adversarial Networks for Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015910825","doi":"https://doi.org/10.1109/icassp40776.2020.9054256","mag":"3015910825"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054256","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/A5009777472","display_name":"Peishuo Li","orcid":"https://orcid.org/0000-0002-6293-1826"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peishuo Li","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072421286","display_name":"Zihang Jiang","orcid":"https://orcid.org/0000-0002-8096-842X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihang Jiang","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054524841","display_name":"Shouyi Yin","orcid":"https://orcid.org/0000-0003-2309-572X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouyi Yin","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039153635","display_name":"Dandan Song","orcid":"https://orcid.org/0000-0002-7239-6900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dandan Song","raw_affiliation_strings":["TsingMicro Co. Ltd"],"affiliations":[{"raw_affiliation_string":"TsingMicro Co. Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086894201","display_name":"Peng Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Ouyang","raw_affiliation_strings":["TsingMicro Co. Ltd"],"affiliations":[{"raw_affiliation_string":"TsingMicro Co. Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358856","display_name":"Leibo Liu","orcid":"https://orcid.org/0000-0001-7548-4116"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leibo Liu","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036023084","display_name":"Shaojun Wei","orcid":"https://orcid.org/0000-0001-5117-7920"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wei","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5009777472"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.9092,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73179724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6234","last_page":"6238"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9940999746322632,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9933000206947327,"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/discriminator","display_name":"Discriminator","score":0.9334198236465454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7630274295806885},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7323806285858154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6325118541717529},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5835774540901184},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5798019170761108},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.519462525844574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48216360807418823},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4540695250034332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40448975563049316},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.14846181869506836},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13480892777442932},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08385741710662842},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08271357417106628}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9334198236465454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630274295806885},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7323806285858154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6325118541717529},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5835774540901184},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5798019170761108},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.519462525844574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48216360807418823},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4540695250034332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40448975563049316},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.14846181869506836},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13480892777442932},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08385741710662842},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08271357417106628},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054256","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1635512741","https://openalex.org/W2048142341","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2128653836","https://openalex.org/W2141411743","https://openalex.org/W2153894152","https://openalex.org/W2397226255","https://openalex.org/W2404892923","https://openalex.org/W2810518847","https://openalex.org/W2889126820","https://openalex.org/W2892356933","https://openalex.org/W2940177920","https://openalex.org/W2950258612","https://openalex.org/W2963045393","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963981733","https://openalex.org/W2964121592","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W4301206121","https://openalex.org/W6631190155","https://openalex.org/W6712317276","https://openalex.org/W6729966448","https://openalex.org/W6735429107","https://openalex.org/W6765779288"],"related_works":["https://openalex.org/W2953246223","https://openalex.org/W4293320219","https://openalex.org/W3110074278","https://openalex.org/W4283584549","https://openalex.org/W2618858825","https://openalex.org/W2554314924","https://openalex.org/W2998859928","https://openalex.org/W3156863413","https://openalex.org/W4381885966","https://openalex.org/W4288256692"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"are":[4],"becoming":[5],"more":[6,8,66,75,117],"and":[7,24,31,80,120],"popular":[9],"in":[10],"speech":[11,16,33,38,124],"enhancement.":[12],"Most":[13],"of":[14,63,102,112],"DNN-based":[15],"enhancement":[17,39,125],"approaches":[18],"currently":[19],"operate":[20],"on":[21],"magnitude":[22],"spectra":[23],"ignore":[25],"the":[26,37,49,69,84,88,100,123],"phase":[27,50,79,89],"mismatch":[28,51],"between":[29],"noisy":[30,78,105],"clean":[32],"which":[34],"greatly":[35],"limits":[36],"performance.":[40,126],"This":[41],"paper":[42],"presents":[43],"a":[44,59,65,94,116],"new":[45,95],"approach":[46],"to":[47,73,77,82,98,104],"solve":[48],"problem":[52],"by":[53,87],"training":[54],"traditional":[55],"DNN":[56,70],"adversarially":[57],"with":[58],"time-domain":[60,113],"discriminator.":[61],"Instead":[62],"estimating":[64],"accurate":[67],"phase,":[68],"is":[71],"trained":[72],"be":[74],"adapted":[76],"able":[81],"minimize":[83],"influence":[85],"brought":[86],"mismatch.":[90],"We":[91],"also":[92],"propose":[93],"evaluation":[96],"metric":[97],"judge":[99],"degree":[101],"adaptation":[103],"phase.":[106],"Experimental":[107],"results":[108],"show":[109],"that":[110],"adding":[111],"discriminator":[114],"yields":[115],"phase-adapted":[118],"generator":[119],"significantly":[121],"improves":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}