{"id":"https://openalex.org/W4408353565","doi":"https://doi.org/10.1109/icassp49660.2025.10887569","title":"Noise-Robust Speech Emotion Recognition Using Shared Self-Supervised Representations with Integrated Speech Enhancement","display_name":"Noise-Robust Speech Emotion Recognition Using Shared Self-Supervised Representations with Integrated Speech Enhancement","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353565","doi":"https://doi.org/10.1109/icassp49660.2025.10887569"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5113145213","display_name":"Jing-Tong Tzeng","orcid":"https://orcid.org/0000-0002-2053-0581"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jing-Tong Tzeng","raw_affiliation_strings":["National Tsing Hua University,College of Semiconductor Research,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,College of Semiconductor Research,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","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":false,"raw_author_name":"Seong-Gyun Leem","raw_affiliation_strings":["The University of Texas at Dallas,Department of Electrical and Computer Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030061643","display_name":"Ali N. Salman","orcid":"https://orcid.org/0000-0003-1395-0382"},"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":"Ali N. Salman","raw_affiliation_strings":["The University of Texas at Dallas,Department of Electrical and Computer Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086107623","display_name":"Chi-Chun Lee","orcid":"https://orcid.org/0000-0003-0186-4321"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":["National Tsing Hua University,College of Semiconductor Research,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,College of Semiconductor Research,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"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":["The University of Texas at Dallas,Department of Electrical and Computer Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Department of Electrical and Computer Engineering,USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.1178,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98801267,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9607999920845032,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9607999920845032,"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/T10860","display_name":"Speech and Audio Processing","score":0.9528999924659729,"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-enhancement","display_name":"Speech enhancement","score":0.7812799215316772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7571825981140137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.703433632850647},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5344101190567017},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5275399684906006},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4955407381057739},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3998100459575653},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36141759157180786},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20886391401290894}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7812799215316772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7571825981140137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703433632850647},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5344101190567017},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5275399684906006},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4955407381057739},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3998100459575653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36141759157180786},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20886391401290894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":33,"referenced_works":["https://openalex.org/W202727379","https://openalex.org/W2146334809","https://openalex.org/W2603567530","https://openalex.org/W2742542661","https://openalex.org/W2790326622","https://openalex.org/W2806649730","https://openalex.org/W2963914279","https://openalex.org/W2972852081","https://openalex.org/W3081192838","https://openalex.org/W3095093565","https://openalex.org/W3128401974","https://openalex.org/W3164582967","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224933371","https://openalex.org/W4224933800","https://openalex.org/W4225635674","https://openalex.org/W4226403810","https://openalex.org/W4319862462","https://openalex.org/W4372267458","https://openalex.org/W4385822811","https://openalex.org/W4389459413","https://openalex.org/W4390874791","https://openalex.org/W4392903309","https://openalex.org/W4400615821","https://openalex.org/W4402111232","https://openalex.org/W6746278845","https://openalex.org/W6757817989","https://openalex.org/W6780218876","https://openalex.org/W6790758941","https://openalex.org/W6856619237"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2904739811","https://openalex.org/W2051376034","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"demonstrated":[3],"the":[4,39,93,112,121,131,165,178],"effectiveness":[5],"of":[6,133],"fine-tuning":[7],"self-supervised":[8,47,78],"speech":[9,13,36,48,53,70],"representation":[10,49],"models":[11],"for":[12,51,100],"emotion":[14,54,84],"recognition":[15,55],"(SER).":[16],"However,":[17],"applying":[18],"SER":[19,62,74,101,124,141],"in":[20,61,87,140,170,174],"real-world":[21],"environments":[22],"remains":[23],"challenging":[24],"due":[25,33],"to":[26,34,57,82,96],"pervasive":[27],"noise.":[28],"Relying":[29],"on":[30],"low-accuracy":[31],"predictions":[32],"noisy":[35,88,145],"can":[37],"undermine":[38],"user\u2019s":[40],"trust.":[41],"This":[42,90,136],"paper":[43],"proposes":[44],"a":[45,106,154],"unified":[46],"framework":[50,68],"enhanced":[52,65],"designed":[56],"increase":[58],"noise":[59],"robustness":[60],"while":[63],"generating":[64],"speech.":[66],"Our":[67],"integrates":[69],"enhancement":[71],"(SE)":[72],"and":[73,118,123,129,172],"tasks,":[75],"leveraging":[76],"shared":[77],"learning":[79],"(SSL)-derived":[80],"features":[81],"improve":[83],"classification":[85],"performance":[86,142],"environments.":[89],"strategy":[91],"encourages":[92],"SE":[94,122,149],"module":[95],"enhance":[97],"discriminative":[98],"information":[99],"tasks.":[102],"Additionally,":[103],"we":[104],"introduce":[105],"cascade":[107],"unfrozen":[108,117],"training":[109,127],"strategy,":[110],"where":[111,177],"SSL":[113,134],"model":[114],"is":[115],"gradually":[116],"fine-tuned":[119],"alongside":[120],"heads,":[125],"ensuring":[126],"stability":[128],"preserving":[130],"generalizability":[132],"representations.":[135],"approach":[137],"demonstrates":[138],"improvements":[139],"under":[143],"unseen":[144],"conditions":[146],"without":[147],"compromising":[148],"quality.":[150],"When":[151],"tested":[152],"at":[153],"0":[155],"dB":[156],"signal-to-noise":[157],"ratio":[158],"(SNR)":[159],"level,":[160],"our":[161],"proposed":[162],"method":[163],"outperforms":[164],"original":[166],"baseline":[167],"by":[168],"3.7%":[169],"F1-Macro":[171],"2.7%":[173],"F1-Micro":[175],"scores,":[176],"differences":[179],"are":[180],"statistically":[181],"significant.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":8}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}