{"id":"https://openalex.org/W4391021654","doi":"https://doi.org/10.1109/asru57964.2023.10389753","title":"Combining Relative and Absolute Learning Formulations to Predict Emotional Attributes From Speech","display_name":"Combining Relative and Absolute Learning Formulations to Predict Emotional Attributes From Speech","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021654","doi":"https://doi.org/10.1109/asru57964.2023.10389753"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389753","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5021565289","display_name":"Abinay Reddy Naini","orcid":null},"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":"Abinay Reddy Naini","raw_affiliation_strings":["The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064605752","display_name":"Shruthi Subramanium","orcid":null},"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":"Shruthi Subramanium","raw_affiliation_strings":["The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"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,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]},{"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,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas,Multimodal Signal Processing (MSP) Laboratory,Department of Electrical and Computer Engineering,Richardson,TX,USA,75080","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23967552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":1.0,"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":1.0,"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":0.9961000084877014,"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":0.9904999732971191,"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":0.587074339389801},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5677065253257751},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5658543109893799},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5495010614395142},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.5465556979179382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082073211669922},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4962826371192932},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4949910044670105},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.47988665103912354},{"id":"https://openalex.org/keywords/emotional-valence","display_name":"Emotional valence","score":0.4444265365600586},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.44096407294273376},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3696839213371277},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33658868074417114},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.33462047576904297},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.2868603467941284},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2755297124385834},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19597139954566956},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18387851119041443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.587074339389801},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5677065253257751},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5658543109893799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5495010614395142},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.5465556979179382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082073211669922},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4962826371192932},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4949910044670105},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.47988665103912354},{"id":"https://openalex.org/C3020774634","wikidata":"https://www.wikidata.org/wiki/Q3113318","display_name":"Emotional valence","level":3,"score":0.4444265365600586},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.44096407294273376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3696839213371277},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33658868074417114},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33462047576904297},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2868603467941284},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2755297124385834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19597139954566956},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18387851119041443},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389753","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":31,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1993008008","https://openalex.org/W2026984028","https://openalex.org/W2032254851","https://openalex.org/W2143331230","https://openalex.org/W2156848952","https://openalex.org/W2181873835","https://openalex.org/W2400120934","https://openalex.org/W2404446881","https://openalex.org/W2508783453","https://openalex.org/W2673304402","https://openalex.org/W2696559478","https://openalex.org/W2742542661","https://openalex.org/W2806649730","https://openalex.org/W2889090126","https://openalex.org/W2889113107","https://openalex.org/W2899500748","https://openalex.org/W2900358852","https://openalex.org/W2980282514","https://openalex.org/W2996156641","https://openalex.org/W3016153892","https://openalex.org/W3198771897","https://openalex.org/W4230277160","https://openalex.org/W4313639160","https://openalex.org/W4361994820","https://openalex.org/W4372189490","https://openalex.org/W4385822566","https://openalex.org/W4390874415","https://openalex.org/W6631190155","https://openalex.org/W6768817161","https://openalex.org/W6853398190"],"related_works":["https://openalex.org/W4243820032","https://openalex.org/W2915671565","https://openalex.org/W4312138225","https://openalex.org/W4252711001","https://openalex.org/W2015330565","https://openalex.org/W4385436741","https://openalex.org/W4283756072","https://openalex.org/W3106026632","https://openalex.org/W2034258736","https://openalex.org/W2129455854"],"abstract_inverted_index":{"Predicting":[0],"absolute":[1,59,80,112],"scores":[2,113],"is":[3,32,45],"the":[4,49,99,125,134,137],"most":[5],"common":[6],"speech-emotion":[7],"recognition":[8],"(SER)":[9],"task":[10,130],"when":[11],"predicting":[12],"emotional":[13,88],"attributes":[14],"(i.e.,":[15],"valence,":[16],"arousal,":[17],"and":[18,60,77],"dominance).":[19],"However,":[20],"studies":[21],"have":[22],"shown":[23],"that":[24,105],"emotion":[25],"has":[26],"an":[27],"ordinal":[28],"nature":[29],"where":[30],"it":[31],"more":[33,46],"reliable":[34],"to":[35,57,86,101,109,124],"establish":[36],"a":[37,54,83],"preference":[38,73],"between":[39,74],"speech":[40,75],"samples":[41,76],"(e.g.,":[42],"one":[43,129],"sample":[44],"positive":[47],"than":[48],"other).":[50],"This":[51],"paper":[52],"pursues":[53],"novel":[55],"direction":[56],"combine":[58],"relative":[61],"learning":[62],"formulations":[63],"for":[64],"SER.":[65],"The":[66,117],"proposed":[67],"multitask":[68,118],"formulation":[69],"can":[70,120],"simultaneously":[71],"estimate":[72,115],"predict":[78,111],"their":[79],"score,":[81],"providing":[82],"flexible":[84],"tool":[85],"analyze":[87],"content":[89],"in":[90],"speech.":[91],"Both":[92],"tasks":[93],"mutually":[94],"complement":[95],"each":[96],"other,":[97],"allowing":[98],"model":[100],"outperform":[102],"SER":[103],"systems":[104],"are":[106],"exclusively":[107],"trained":[108],"either":[110],"or":[114],"preferences.":[116],"weights":[119],"be":[121],"set":[122],"according":[123],"intended":[126],"applications,":[127],"prioritizing":[128],"while":[131],"slightly":[132],"compromising":[133],"performance":[135],"of":[136],"other":[138],"task.":[139]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}