{"id":"https://openalex.org/W4294069577","doi":"https://doi.org/10.1109/icce-taiwan55306.2022.9869259","title":"Improving the performance of DEMUCS in speech enhancement with the perceptual metric loss","display_name":"Improving the performance of DEMUCS in speech enhancement with the perceptual metric loss","publication_year":2022,"publication_date":"2022-07-06","ids":{"openalex":"https://openalex.org/W4294069577","doi":"https://doi.org/10.1109/icce-taiwan55306.2022.9869259"},"language":"en","primary_location":{"id":"doi:10.1109/icce-taiwan55306.2022.9869259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-taiwan55306.2022.9869259","pdf_url":null,"source":{"id":"https://openalex.org/S4363607852","display_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059759873","display_name":"Zong-Tai Wu","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":"Zong-Tai Wu","raw_affiliation_strings":["National Chi Nan University,Taiwan","National Chi Nan University, Taiwan"],"raw_orcid":null,"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/A5010100753","display_name":"Yan-Tong Chen","orcid":"https://orcid.org/0009-0008-5528-1379"},"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":"Yan-Tong Chen","raw_affiliation_strings":["National Chi Nan University,Taiwan","National Chi Nan University, Taiwan"],"raw_orcid":null,"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":"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193365169"],"apc_list":null,"apc_paid":null,"fwci":0.1846,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35043323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"267","last_page":"268"},"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":0.996399998664856,"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":0.9954000115394592,"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/pesq","display_name":"PESQ","score":0.9708794355392456},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8015415668487549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7152329087257385},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6670044660568237},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6548860669136047},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.5408076047897339},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5027644634246826},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.43594419956207275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34549614787101746},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.2881499230861664},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1454702913761139},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09213876724243164},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08798623085021973},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.07874855399131775}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9708794355392456},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8015415668487549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152329087257385},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6670044660568237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6548860669136047},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.5408076047897339},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5027644634246826},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43594419956207275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34549614787101746},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.2881499230861664},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1454702913761139},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09213876724243164},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08798623085021973},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.07874855399131775},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/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-taiwan55306.2022.9869259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icce-taiwan55306.2022.9869259","pdf_url":null,"source":{"id":"https://openalex.org/S4363607852","display_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Consumer Electronics - Taiwan","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2141998673","https://openalex.org/W2603567530","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2990594533","https://openalex.org/W3096893582","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3209141406","https://openalex.org/W6802983977"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W1823208675","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W2166831097","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"This":[0],"study":[1],"attempts":[2],"to":[3,14,39,48,70,91],"revise":[4],"the":[5,10,44,50,55,60,73,93,107,115,121],"loss":[6,51,58],"function":[7,46,52],"used":[8],"in":[9],"well-known":[11],"method,":[12],"DEMUCS,":[13,43],"improve":[15],"its":[16],"speech":[17,40,78,83,122],"enhancement":[18,123],"performance.":[19],"DEMUCS":[20,94,126],"is":[21,47],"a":[22],"celebrated":[23],"deep":[24],"learning":[25],"architecture":[26],"initially":[27],"designed":[28],"for":[29,77],"audio":[30],"source":[31],"separation,":[32],"while":[33],"it":[34],"can":[35,127],"also":[36],"be":[37,128],"applied":[38],"enhancement.":[41],"In":[42],"objective":[45,88],"minimize":[49],"that":[53,101],"contains":[54],"time-domain":[56],"waveform":[57],"and":[59,86,113,118],"multi-resolution":[61],"short-time":[62,87],"Fourier":[63],"transform":[64],"(STFT)":[65],"loss.":[66],"Here,":[67],"we":[68],"propose":[69],"directly":[71],"adopt":[72],"perceptual":[74,82,109],"metric-aware":[75],"losses":[76],"enhancement,":[79],"which":[80],"involve":[81],"quality":[84],"(PESQ)":[85],"intelligibility":[89],"(STOI)":[90],"learn":[92],"network.":[95],"The":[96],"preliminary":[97],"experimental":[98],"results":[99],"indicate":[100],"when":[102],"jointly":[103],"optimizing":[104],"either":[105],"of":[106,125],"two":[108],"metrics":[110],"(PESQ,":[111],"STOI)":[112],"minimizing":[114],"original":[116],"time-":[117],"spectral-domain":[119],"losses,":[120],"performance":[124],"further":[129],"promoted.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}