{"id":"https://openalex.org/W4392903124","doi":"https://doi.org/10.1109/icassp48485.2024.10446606","title":"Investigating Salient Representations and Label Variance in Dimensional Speech Emotion Analysis","display_name":"Investigating Salient Representations and Label Variance in Dimensional Speech Emotion Analysis","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903124","doi":"https://doi.org/10.1109/icassp48485.2024.10446606"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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":true,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082699365","display_name":"Jingping Nie","orcid":"https://orcid.org/0000-0002-9181-8398"},"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":"Jingping Nie","raw_affiliation_strings":["Apple"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091201226"],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":1.0624,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75733533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11111","last_page":"11115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9959999918937683,"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/T11309","display_name":"Music and Audio Processing","score":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.7400116324424744},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7235192060470581},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.621189534664154},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5865105986595154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44388478994369507},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.42286908626556396},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41933560371398926},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4192253053188324},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.41481897234916687},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.41376838088035583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3346720337867737},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14963945746421814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400116324424744},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7235192060470581},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.621189534664154},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5865105986595154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44388478994369507},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.42286908626556396},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41933560371398926},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4192253053188324},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.41481897234916687},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.41376838088035583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3346720337867737},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14963945746421814},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":22,"referenced_works":["https://openalex.org/W129316862","https://openalex.org/W1966797434","https://openalex.org/W2050730017","https://openalex.org/W2146334809","https://openalex.org/W2165857685","https://openalex.org/W2313339984","https://openalex.org/W2401417847","https://openalex.org/W2515456817","https://openalex.org/W2742542661","https://openalex.org/W2752234108","https://openalex.org/W2972951327","https://openalex.org/W2973034847","https://openalex.org/W2999747565","https://openalex.org/W3004449907","https://openalex.org/W3096690837","https://openalex.org/W3209059054","https://openalex.org/W3215155711","https://openalex.org/W4221161909","https://openalex.org/W4284960025","https://openalex.org/W4309969834","https://openalex.org/W4372270176","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W1484111231","https://openalex.org/W4391160746","https://openalex.org/W3125756894","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W3089231081"],"abstract_inverted_index":{"Representations":[0,9],"derived":[1],"from":[2,10],"models":[3,53,124],"such":[4,106],"as":[5],"BERT":[6],"(Bidirectional":[7],"Encoder":[8],"Transformers)":[11],"and":[12,32,57,103,114,128],"Hu-BERT":[13],"(Hidden":[14],"units":[15],"BERT),":[16],"have":[17],"helped":[18],"to":[19,48,137,142],"achieve":[20],"state-of-the-art":[21],"performance":[22,86,140],"in":[23,80,96,149],"dimensional":[24,133,150],"speech":[25,51],"emotion":[26,41,52,88,123,151],"recognition.":[27],"Despite":[28],"their":[29],"large":[30,50],"dimensionality,":[31],"even":[33],"though":[34],"these":[35,72],"representations":[36,134,145],"are":[37,45],"not":[38],"tailored":[39],"for":[40],"recognition":[42],"tasks,":[43],"they":[44],"frequently":[46],"used":[47],"train":[49],"with":[54],"high":[55],"memory":[56],"computational":[58],"costs.":[59],"In":[60,90],"this":[61],"work,":[62],"we":[63,92,117],"show":[64],"that":[65,76,105,130],"there":[66],"exist":[67],"lower-dimensional":[68],"subspaces":[69],"within":[70],"the":[71,97,110,119,122,131,139,143],"pre-trained":[73],"representational":[74],"spaces":[75],"offer":[77],"a":[78],"reduction":[79],"downstream":[81],"model":[82,93],"complexity":[83],"without":[84,146],"sacrificing":[85],"on":[87],"estimation.":[89],"addition,":[91],"label":[94],"uncertainty":[95],"form":[98],"of":[99,121],"grader":[100],"opinion":[101],"variance,":[102],"demonstrate":[104],"information":[107],"can":[108],"improve":[109],"model\u2019s":[111],"generalization":[112],"capacity":[113],"robustness.":[115],"Finally,":[116],"compare":[118],"robustness":[120],"against":[125],"acoustic":[126],"degradations":[127],"observed":[129],"reduced":[132],"were":[135],"able":[136],"retain":[138],"similar":[141],"full-dimensional":[144],"significant":[147],"regression":[148],"performance.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}