{"id":"https://openalex.org/W4296069347","doi":"https://doi.org/10.21437/interspeech.2022-10478","title":"Perceptual Contrast Stretching on Target Feature for Speech Enhancement","display_name":"Perceptual Contrast Stretching on Target Feature for Speech Enhancement","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069347","doi":"https://doi.org/10.21437/interspeech.2022-10478"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10478","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10478","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5110793574","display_name":"Rong Chao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Rong Chao","raw_affiliation_strings":["CITI, Academia Sinica, Taiwan","CSIE, NCKU, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CITI, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"CSIE, NCKU, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622632","display_name":"Cheng Yu","orcid":"https://orcid.org/0000-0003-4816-1586"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng Yu","raw_affiliation_strings":["CITI, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CITI, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Szu-wei Fu","raw_affiliation_strings":["Microsoft Corporation 4 NICT, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation 4 NICT, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["CITI, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CITI, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044008055"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":4.0605,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95681474,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5448","last_page":"5452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9907000064849854,"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":0.9907000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.7514859437942505},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6328974366188049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6315368413925171},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6315292716026306},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.542645275592804},{"id":"https://openalex.org/keywords/contrast-enhancement","display_name":"Contrast enhancement","score":0.4901169240474701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4596417248249054},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3543713092803955},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3390580415725708},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.19473275542259216},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11116418242454529},{"id":"https://openalex.org/keywords/magnetic-resonance-imaging","display_name":"Magnetic resonance imaging","score":0.0872575044631958},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.06795993447303772},{"id":"https://openalex.org/keywords/radiology","display_name":"Radiology","score":0.05411618947982788}],"concepts":[{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.7514859437942505},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6328974366188049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6315368413925171},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6315292716026306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.542645275592804},{"id":"https://openalex.org/C3018181011","wikidata":"https://www.wikidata.org/wiki/Q6849688","display_name":"Contrast enhancement","level":3,"score":0.4901169240474701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4596417248249054},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3543713092803955},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3390580415725708},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.19473275542259216},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11116418242454529},{"id":"https://openalex.org/C143409427","wikidata":"https://www.wikidata.org/wiki/Q161238","display_name":"Magnetic resonance imaging","level":2,"score":0.0872575044631958},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.06795993447303772},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.05411618947982788},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10478","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10478","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W190902214","https://openalex.org/W1790748249","https://openalex.org/W1897240248","https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2128653836","https://openalex.org/W2153894152","https://openalex.org/W2291877678","https://openalex.org/W2402901296","https://openalex.org/W2405774341","https://openalex.org/W2534171296","https://openalex.org/W2594607416","https://openalex.org/W2718052359","https://openalex.org/W2746457594","https://openalex.org/W2755891984","https://openalex.org/W2757519008","https://openalex.org/W2799963040","https://openalex.org/W2809941692","https://openalex.org/W2949558265","https://openalex.org/W2963341071","https://openalex.org/W2972443522","https://openalex.org/W3015895387","https://openalex.org/W3016129867","https://openalex.org/W3016912202","https://openalex.org/W3027637851","https://openalex.org/W3095248373","https://openalex.org/W3097945073","https://openalex.org/W3132954452","https://openalex.org/W3158779859","https://openalex.org/W3167533889","https://openalex.org/W3196888558","https://openalex.org/W3197284240","https://openalex.org/W3207256499","https://openalex.org/W4230441359","https://openalex.org/W4236555067","https://openalex.org/W4287236406","https://openalex.org/W4301350573"],"related_works":["https://openalex.org/W2163751115","https://openalex.org/W2625093041","https://openalex.org/W2733233723","https://openalex.org/W769135352","https://openalex.org/W2110445265","https://openalex.org/W2269162818","https://openalex.org/W2415838370","https://openalex.org/W3120218437","https://openalex.org/W1981560124","https://openalex.org/W3043297934"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"(SE)":[2],"performance":[3,80,122],"has":[4],"improved":[5],"considerably":[6],"owing":[7],"to":[8,27,45],"the":[9,37,47,50,53,66,76,101,111,116],"use":[10],"of":[11,49,55,105],"deep":[12],"learning":[13],"models":[14],"as":[15],"a":[16,21],"base":[17],"function.Herein,":[18],"we":[19],"propose":[20],"perceptual":[22,62],"contrast":[23,54],"stretching":[24],"(PCS)":[25],"approach":[26],"further":[28],"improve":[29],"SE":[30,51,68,91,106,136],"performance.The":[31],"PCS":[32,74,85,97],"is":[33,43,58],"derived":[34],"based":[35,60],"on":[36,61,110,123],"critical":[38],"band":[39],"importance":[40],"function":[41],"and":[42,81,94,130],"applied":[44],"modify":[46],"targets":[48],"model.Specifically,":[52],"target":[56],"features":[57],"stretched":[59],"importance,":[63],"thereby":[64],"improving":[65],"overall":[67],"performance.Compared":[69],"with":[70,89],"post-processing-based":[71],"implementations,":[72],"incorporating":[73],"into":[75],"training":[77,95],"phase":[78],"preserves":[79],"reduces":[82],"online":[83],"computation.Notably,":[84],"can":[86,119],"be":[87],"combined":[88],"different":[90],"model":[92,107],"architectures":[93],"criteria.Furthermore,":[96],"does":[98],"not":[99],"affect":[100],"causality":[102],"or":[103],"convergence":[104],"training.Experimental":[108],"results":[109],"VoiceBank-DEMAND":[112],"dataset":[113],"show":[114],"that":[115],"proposed":[117],"method":[118],"achieve":[120],"state-of-the-art":[121],"both":[124],"causal":[125],"(PESQ":[126,132],"score":[127,133],"=":[128,134],"3.07)":[129],"noncausal":[131],"3.35)":[135],"tasks.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}