{"id":"https://openalex.org/W4386322308","doi":"https://doi.org/10.1109/icce-taiwan58799.2023.10226904","title":"Improving the performance of CMGAN in speech enhancement with the phone fortified perceptual loss","display_name":"Improving the performance of CMGAN in speech enhancement with the phone fortified perceptual loss","publication_year":2023,"publication_date":"2023-07-17","ids":{"openalex":"https://openalex.org/W4386322308","doi":"https://doi.org/10.1109/icce-taiwan58799.2023.10226904"},"language":"en","primary_location":{"id":"doi:10.1109/icce-taiwan58799.2023.10226904","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce-taiwan58799.2023.10226904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","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/A5070560498","display_name":"Chi-En Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chi-En Dai","raw_affiliation_strings":["National Chi Nan University,Taiwan","National Chi Nan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"National Chi Nan University, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109634840","display_name":"Jia-Xuan Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Xuan Zeng","raw_affiliation_strings":["National Chi Nan University,Taiwan","National Chi Nan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"National Chi Nan University, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114068090","display_name":"Wan-Ling Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wan-Ling Zeng","raw_affiliation_strings":["National Chi Nan University,Taiwan","National Chi Nan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"National Chi Nan University, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087392653","display_name":"Eric S. Li","orcid":"https://orcid.org/0000-0003-3252-4346"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Eric S. Li","raw_affiliation_strings":["National Taipei University of Technology,Taiwan","National Taipei University of Technology, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taipei University of Technology,Taiwan","institution_ids":["https://openalex.org/I118292597"]},{"raw_affiliation_string":"National Taipei University of Technology, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-Weih Hung","raw_affiliation_strings":["National Chi Nan University,Taiwan","National Chi Nan University, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chi Nan University,Taiwan","institution_ids":["https://openalex.org/I193365169"]},{"raw_affiliation_string":"National Chi Nan University, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070560498"],"corresponding_institution_ids":["https://openalex.org/I193365169"],"apc_list":null,"apc_paid":null,"fwci":0.1995,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43934792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"459","last_page":"460"},"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7157772183418274},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6572698950767517},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.6464133262634277},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5820508003234863},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5700773000717163},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5667087435722351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47513988614082336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40267422795295715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3339523673057556},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.24998220801353455},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14582547545433044},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12479531764984131},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.0919865071773529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157772183418274},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6572698950767517},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6464133262634277},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5820508003234863},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5700773000717163},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5667087435722351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47513988614082336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40267422795295715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3339523673057556},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.24998220801353455},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14582547545433044},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12479531764984131},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0919865071773529},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icce-taiwan58799.2023.10226904","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icce-taiwan58799.2023.10226904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2141998673","https://openalex.org/W2603567530","https://openalex.org/W2949558265","https://openalex.org/W2962795274","https://openalex.org/W2963341071","https://openalex.org/W2973049979","https://openalex.org/W3096159803","https://openalex.org/W3096992656","https://openalex.org/W3209141406","https://openalex.org/W4221143458","https://openalex.org/W6762114000","https://openalex.org/W6784878386","https://openalex.org/W6802983977"],"related_works":["https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W3110074278","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W3156863413","https://openalex.org/W4381885966","https://openalex.org/W2969399009"],"abstract_inverted_index":{"This":[0],"study":[1,81],"aims":[2],"to":[3,37,90,149],"promote":[4],"the":[5,14,39,42,46,64,68,72,76,84,94,97,107,110,116,133,138,141,144,154,162],"usage":[6],"of":[7,41,96,140],"a":[8,25,33,150],"renowned":[9],"speech":[10],"enhancement":[11,152],"method,":[12],"namely":[13],"Conformer-based":[15],"Metric":[16],"Generative":[17],"Adversarial":[18],"Network":[19],"(CMGAN).":[20],"The":[21,49,79,127],"CMGAN":[22,53,145],"model":[23],"utilizes":[24],"generative":[26],"adversarial":[27],"network":[28,51],"(GAN)":[29],"architecture":[30],"and":[31,71,122,158],"incorporates":[32],"Conformer-":[34],"based":[35],"metric":[36],"assess":[38],"quality":[40],"synthetic":[43,120],"data":[44,121],"from":[45,59],"generator":[47,50],"network.":[48,78],"in":[52,153],"derives":[54],"its":[55],"loss":[56,73,85,101],"function":[57,86],"primarily":[58],"three":[60],"distinct":[61],"sources,":[62],"namely:":[63],"time-frequency":[65],"domain":[66],"loss,":[67,70],"waveform-domain":[69],"fed":[74],"by":[75,115],"discriminator":[77],"present":[80],"posits":[82],"that":[83,123,137],"can":[87],"be":[88],"subject":[89],"further":[91],"revision":[92],"through":[93],"incorporation":[95,139],"phone-":[98],"fortified":[99],"perceptual":[100],"(PFPL).":[102],"PFPL":[103,142],"is":[104],"observed":[105],"as":[106],"difference":[108],"between":[109],"latent":[111],"phone-level":[112],"representation":[113],"generated":[114],"wave2vec":[117],"encoder":[118],"for":[119,124,161],"real":[125],"data.":[126,164],"preliminary":[128],"experiments":[129],"carried":[130],"out":[131],"on":[132],"VoiceBank-DEMAND":[134],"task":[135],"suggest":[136],"into":[143],"learning":[146],"process":[147],"leads":[148],"notable":[151],"objective":[155],"metrics":[156],"(PESQ":[157],"STOI)":[159],"scores":[160],"test":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}