{"id":"https://openalex.org/W4389459413","doi":"https://doi.org/10.1109/taslp.2023.3340603","title":"Selective Acoustic Feature Enhancement for Speech Emotion Recognition With Noisy Speech","display_name":"Selective Acoustic Feature Enhancement for Speech Emotion Recognition With Noisy Speech","publication_year":2023,"publication_date":"2023-12-07","ids":{"openalex":"https://openalex.org/W4389459413","doi":"https://doi.org/10.1109/taslp.2023.3340603","pmid":"https://pubmed.ncbi.nlm.nih.gov/39015743"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3340603","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3340603","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10347397.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10347397.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024273749","display_name":"Seong-Gyun Leem","orcid":"https://orcid.org/0000-0002-1175-1577"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Seong-Gyun Leem","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA","Electrical and Computer Engineering, The University of Texas at Dallas Erik Jonsson School of Engineering and Computer Science, Richardson, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Electrical and Computer Engineering, The University of Texas at Dallas Erik Jonsson School of Engineering and Computer Science, Richardson, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026166163","display_name":"Daniel Fulford","orcid":"https://orcid.org/0000-0003-4405-9031"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Fulford","raw_affiliation_strings":["Occupational Therapy and Psychological and Brain Sciences, Boston University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Occupational Therapy and Psychological and Brain Sciences, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041695925","display_name":"Jukka\u2010Pekka Onnela","orcid":"https://orcid.org/0000-0001-6613-8668"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jukka-Pekka Onnela","raw_affiliation_strings":["Department of Biostatistics, Harvard T.H. Chan School of Public Health, Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007724150","display_name":"David E. Gard","orcid":"https://orcid.org/0000-0002-0446-4000"},"institutions":[{"id":"https://openalex.org/I71838634","display_name":"San Francisco State University","ror":"https://ror.org/05ykr0121","country_code":"US","type":"education","lineage":["https://openalex.org/I71838634"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Gard","raw_affiliation_strings":["Department of Psychology, San Francisco State University, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Psychology, San Francisco State University, San Francisco, CA, USA","institution_ids":["https://openalex.org/I71838634"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5024273749"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":4.4921,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95876097,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"917","last_page":"929"},"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/speech-recognition","display_name":"Speech recognition","score":0.7870786786079407},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5921348929405212},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5690915584564209},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5682973861694336},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5546172261238098},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2111474573612213},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.150270015001297},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1089043915271759}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7870786786079407},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5921348929405212},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5690915584564209},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5682973861694336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5546172261238098},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2111474573612213},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.150270015001297},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1089043915271759},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2023.3340603","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3340603","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10347397.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:39015743","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39015743","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11250502","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11250502","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11250502/pdf/nihms-1955419.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3340603","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3340603","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10347397.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6600000262260437}],"awards":[{"id":"https://openalex.org/G5122359493","display_name":null,"funder_award_id":"1R01MH122367-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389459413.pdf","grobid_xml":"https://content.openalex.org/works/W4389459413.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W1510355813","https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1977775600","https://openalex.org/W1999846783","https://openalex.org/W2044893557","https://openalex.org/W2082492120","https://openalex.org/W2085662862","https://openalex.org/W2096779346","https://openalex.org/W2109378630","https://openalex.org/W2128653836","https://openalex.org/W2130917731","https://openalex.org/W2141998673","https://openalex.org/W2146334809","https://openalex.org/W2147062276","https://openalex.org/W2149535104","https://openalex.org/W2157331557","https://openalex.org/W2165899180","https://openalex.org/W2287742606","https://openalex.org/W2289394825","https://openalex.org/W2401417847","https://openalex.org/W2405774341","https://openalex.org/W2511508976","https://openalex.org/W2525412388","https://openalex.org/W2626544737","https://openalex.org/W2742542661","https://openalex.org/W2747172199","https://openalex.org/W2791210709","https://openalex.org/W2892921685","https://openalex.org/W2902806526","https://openalex.org/W2911336608","https://openalex.org/W2937484199","https://openalex.org/W2940275453","https://openalex.org/W2962839749","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W2963914279","https://openalex.org/W2972852081","https://openalex.org/W2998832642","https://openalex.org/W3002904085","https://openalex.org/W3015249983","https://openalex.org/W3086923691","https://openalex.org/W3102190437","https://openalex.org/W3147539069","https://openalex.org/W3182112704","https://openalex.org/W3196749180","https://openalex.org/W3197042120","https://openalex.org/W3208439161","https://openalex.org/W3209059054","https://openalex.org/W3212119822","https://openalex.org/W4224933371","https://openalex.org/W4297803592","https://openalex.org/W4361994820","https://openalex.org/W4372189490","https://openalex.org/W4372267458","https://openalex.org/W4375869346","https://openalex.org/W6631190155","https://openalex.org/W6632448044","https://openalex.org/W6725448924","https://openalex.org/W6762114000","https://openalex.org/W6772892956","https://openalex.org/W6780218876","https://openalex.org/W6784158405"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"A":[0],"<i>speech":[1,25],"emotion":[2,89],"recognition</i>":[3],"(SER)":[4],"system":[5,35,235],"deployed":[6],"on":[7],"a":[8,24,56,61,109,131,223,234],"real-world":[9],"application":[10],"can":[11,29,49],"encounter":[12],"speech":[13,122,204],"contaminated":[14],"with":[15,21,104,181,208],"unconstrained":[16],"background":[17],"noise.":[18],"To":[19],"deal":[20],"this":[22,77],"issue,":[23],"enhancement</i>":[26],"(SE)":[27],"module":[28,48],"be":[30],"attached":[31],"to":[32,36,73,81,153,195],"the":[33,39,46,51,88,116,142,148,151,154,160,173,182,191,214,219,239,242],"SER":[34,69],"compensate":[37],"for":[38,68,241],"environmental":[40,74],"difference":[41],"of":[42,55,63,156,213],"an":[43,202],"input.":[44],"Although":[45],"SE":[47],"improve":[50],"quality":[52],"and":[53,130,138,210,228],"intelligibility":[54],"given":[57],"speech,":[58],"there":[59],"is":[60,164],"risk":[62],"affecting":[64],"discriminative":[65],"acoustic":[66,106],"features":[67,85,144,149,175],"that":[70,86,135,188,218,236],"are":[71],"resilient":[72,174],"differences.":[75],"Exploring":[76],"idea,":[78],"we":[79,119,166],"propose":[80],"enhance":[82,168],"only":[83,167],"weak":[84,96,143,161,170,192],"degrade":[87],"recognition":[90],"performance.":[91],"Our":[92,206],"model":[93],"first":[94],"identifies":[95],"feature":[97,107,123,162],"sets":[98],"by":[99,124,145],"using":[100,111],"multiple":[101],"models":[102],"trained":[103],"one":[105],"at":[108],"time":[110],"clean":[112,209],"speech.":[113],"After":[114],"training":[115],"single-feature":[117],"models,":[118],"rank":[120,133],"each":[121,157],"measuring":[125],"three":[126],"criteria:":[127],"performance,":[128],"robustness,":[129],"joint":[132],"ranking":[134],"combines":[136],"performance":[137,197,231],"robustness.":[139],"We":[140,177,186],"group":[141],"cumulatively":[146],"incrementing":[147],"from":[150,201],"bottom":[152],"top":[155],"rank.":[158],"Once":[159],"set":[163],"defined,":[165],"those":[169],"features,":[171],"keeping":[172],"unchanged.":[176],"implement":[178],"these":[179],"ideas":[180],"<i>low-level":[183],"descriptors</i>":[184],"(LLDs).":[185],"show":[187],"directly":[189],"enhancing":[190],"LLDs":[193,200,240],"leads":[194],"better":[196],"than":[198],"extracting":[199],"enhanced":[203],"signal.":[205],"experiment":[207],"noisy":[211],"versions":[212],"MSP-Podcast":[215],"corpus":[216],"shows":[217],"proposed":[220],"approach":[221],"yields":[222],"17.7%":[224],"(arousal),":[225],"21.2%":[226],"(dominance),":[227],"3.3%":[229],"(valence)":[230],"gains":[232],"over":[233],"enhances":[237],"all":[238],"10dB":[243],"<i>signal-to-noise":[244],"ratio</i>":[245],"(SNR)":[246],"condition.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}