{"id":"https://openalex.org/W4372270176","doi":"https://doi.org/10.1109/icassp49357.2023.10096968","title":"Pre-Trained Model Representations and Their Robustness Against Noise for Speech Emotion Analysis","display_name":"Pre-Trained Model Representations and Their Robustness Against Noise for Speech Emotion Analysis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372270176","doi":"https://doi.org/10.1109/icassp49357.2023.10096968"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096968","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059094634","display_name":"Vasudha Kowtha","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vasudha Kowtha","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020008681","display_name":"Hsiang-Yun Sherry Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hsiang-Yun Sherry Chien","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090375977","display_name":"Erdrin Azemi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erdrin Azemi","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048751367","display_name":"Carlos Avendano","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Carlos Avendano","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9987999796867371,"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":0.7360468506813049},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7234283685684204},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5411362648010254},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4660293757915497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4349447786808014},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.4228888750076294},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42270639538764954},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3662912845611572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360468506813049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7234283685684204},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5411362648010254},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4660293757915497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4349447786808014},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.4228888750076294},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42270639538764954},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3662912845611572},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096968","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1966797434","https://openalex.org/W2003653478","https://openalex.org/W2313339984","https://openalex.org/W2401417847","https://openalex.org/W2515456817","https://openalex.org/W2587577884","https://openalex.org/W2752234108","https://openalex.org/W2794174306","https://openalex.org/W2896457183","https://openalex.org/W2972852081","https://openalex.org/W2972951327","https://openalex.org/W2973034847","https://openalex.org/W3004449907","https://openalex.org/W3096690837","https://openalex.org/W3197642003","https://openalex.org/W3209059054","https://openalex.org/W3215155711","https://openalex.org/W4221161909","https://openalex.org/W4224933371","https://openalex.org/W4284960025","https://openalex.org/W4323642664","https://openalex.org/W6755207826","https://openalex.org/W6803979805"],"related_works":["https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W4383605217","https://openalex.org/W2041273198","https://openalex.org/W2533508831","https://openalex.org/W1599055764","https://openalex.org/W2742699532","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Pre-trained":[0],"model":[1,49,130,169],"representations":[2,37,50,89,131,143,151],"have":[3,31],"demonstrated":[4,162],"state-of-the-art":[5,95],"performance":[6],"in":[7,108],"speech":[8,40,96],"recognition,":[9],"natural":[10],"language":[11],"processing,":[12],"and":[13,26,35,59,75,99,104,120,134,137,141,161],"other":[14],"applications.":[15,42],"Speech":[16],"models,":[17],"such":[18,55],"as":[19,56],"Bidirectional":[20],"Encoder":[21],"Representations":[22],"from":[23,61,90,166],"Transformers":[24],"(BERT)":[25],"Hidden":[27],"units":[28],"BERT":[29],"(HuBERT),":[30],"enabled":[32],"generating":[33],"lexical":[34,72,121,140,150],"acoustic":[36,80,119,142,159],"to":[38,93,117,155,158,171],"benefit":[39],"recognition":[41],"We":[43,63,147],"investigated":[44,125],"the":[45,126,173],"use":[46],"of":[47,128,175],"pre-trained":[48,91,129],"for":[51],"estimating":[52],"dimensional":[53],"emotions,":[54],"activation,":[57],"valence,":[58],"dominance,":[60],"speech.":[62],"observed":[64],"that":[65,139,149,163],"while":[66],"valence":[67,114],"may":[68],"rely":[69,77],"heavily":[70],"on":[71,79,113],"representations,":[73,160],"activation":[74],"dominance":[76],"mostly":[78],"information.":[81],"In":[82],"this":[83],"work,":[84],"we":[85,100,124],"used":[86],"multi-modal":[87,168],"fusion":[88],"models":[92],"generate":[94],"emotion":[97],"estimation,":[98],"showed":[101],"a":[102,167],"100%":[103],"30%":[105],"relative":[106],"improvement":[107],"concordance":[109],"correlation":[110],"coefficient":[111],"(CCC)":[112],"estimation":[115],"compared":[116,157],"standard":[118],"baselines.":[122],"Finally,":[123],"robustness":[127],"against":[132],"noise":[133],"reverberation":[135],"degradation":[136],"noticed":[138],"are":[144,152],"impacted":[145],"differently.":[146],"discovered":[148],"more":[153],"robust":[154],"distortions":[156],"knowledge":[164],"distillation":[165],"helps":[170],"improve":[172],"noise-robustness":[174],"acoustic-based":[176],"models.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}