{"id":"https://openalex.org/W3215155711","doi":"https://doi.org/10.1109/icassp43922.2022.9747754","title":"Representation Learning Through Cross-Modal Conditional Teacher-Student Training For Speech Emotion Recognition","display_name":"Representation Learning Through Cross-Modal Conditional Teacher-Student Training For Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3215155711","doi":"https://doi.org/10.1109/icassp43922.2022.9747754","mag":"3215155711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747754","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5047128701","display_name":"Sundararajan Srinivasan","orcid":"https://orcid.org/0000-0002-3387-9889"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sundararajan Srinivasan","raw_affiliation_strings":["Amazon AWS AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050484139","display_name":"Zhaocheng Huang","orcid":"https://orcid.org/0000-0002-7915-6790"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaocheng Huang","raw_affiliation_strings":["Amazon AWS AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["Amazon AWS AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon AWS AI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047128701"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":4.8291,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.96078431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6442","last_page":"6446"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.995199978351593,"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":0.7027109861373901},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.6043968796730042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5801007151603699},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5297359228134155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49267107248306274},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.46755966544151306},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.46415600180625916},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.43380439281463623},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42963945865631104},{"id":"https://openalex.org/keywords/concordance-correlation-coefficient","display_name":"Concordance correlation coefficient","score":0.42860379815101624},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.41914892196655273},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1263461410999298},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10612353682518005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7027109861373901},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.6043968796730042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5801007151603699},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5297359228134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49267107248306274},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.46755966544151306},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.46415600180625916},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.43380439281463623},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42963945865631104},{"id":"https://openalex.org/C2781059462","wikidata":"https://www.wikidata.org/wiki/Q5158906","display_name":"Concordance correlation coefficient","level":2,"score":0.42860379815101624},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.41914892196655273},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1263461410999298},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10612353682518005},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/icassp43922.2022.9747754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747754","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W2025905516","https://openalex.org/W2146334809","https://openalex.org/W2156503193","https://openalex.org/W2169166781","https://openalex.org/W2239141610","https://openalex.org/W2313339984","https://openalex.org/W2346454595","https://openalex.org/W2399733683","https://openalex.org/W2576530755","https://openalex.org/W2610961739","https://openalex.org/W2742542661","https://openalex.org/W2803098682","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2936252403","https://openalex.org/W2937833637","https://openalex.org/W2949299266","https://openalex.org/W2963341956","https://openalex.org/W2969889150","https://openalex.org/W3016181583","https://openalex.org/W3032325810","https://openalex.org/W3036601975","https://openalex.org/W3095118468","https://openalex.org/W3096690837","https://openalex.org/W3099782249","https://openalex.org/W3108655343","https://openalex.org/W3148001440","https://openalex.org/W3157923770","https://openalex.org/W3160016036","https://openalex.org/W3162811262","https://openalex.org/W3169320628","https://openalex.org/W3170128710","https://openalex.org/W3179803166","https://openalex.org/W3193714551","https://openalex.org/W3197236059","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3209059054","https://openalex.org/W4226380987","https://openalex.org/W4297808394","https://openalex.org/W6731509202","https://openalex.org/W6755207826","https://openalex.org/W6763572160","https://openalex.org/W6780218876","https://openalex.org/W6792221667","https://openalex.org/W6800061313"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W410723623","https://openalex.org/W2413243053","https://openalex.org/W2015341305","https://openalex.org/W4225593417","https://openalex.org/W2035068594","https://openalex.org/W2129455854","https://openalex.org/W2735297260","https://openalex.org/W4221161909","https://openalex.org/W4286692883"],"abstract_inverted_index":{"Generic":[0],"pre-trained":[1],"speech":[2,17,33,46,113],"and":[3,18,74,162,170],"text":[4,101],"representations":[5,31,47,63],"promise":[6],"to":[7,27,94,141],"reduce":[8],"the":[9,40,57,61,69,85,112,116,124,135,138,167,179],"need":[10],"for":[11,32,48,159],"large":[12],"labeled":[13],"datasets":[14],"on":[15,90,166,178],"specific":[16],"language":[19],"tasks.":[20],"However,":[21,80],"it":[22],"is":[23,64],"not":[24],"clear":[25],"how":[26],"effectively":[28],"adapt":[29],"these":[30],"emotion":[34,49,139],"recognition.":[35],"Recent":[36],"public":[37],"benchmarks":[38],"show":[39,55,82],"efficacy":[41,125],"of":[42,126,134,137,155,174],"several":[43],"popular":[44],"self-supervised":[45],"classification.":[50],"In":[51],"this":[52,105],"study,":[53],"we":[54,81,129],"that":[56,83,98],"primary":[58],"difference":[59],"between":[60],"top-performing":[62],"in":[65,71],"predicting":[66,72],"valence":[67,91,161],"while":[68],"differences":[70],"activation":[73],"dominance":[75,163],"dimensions":[76],"are":[77],"less":[78],"pronounced.":[79],"even":[84],"best-performing":[86],"HuBERT":[87],"representation":[88,114],"underperforms":[89],"prediction":[92],"compared":[93],"a":[95,120,131],"multimodal":[96,117],"model":[97,118],"also":[99,171],"incorporates":[100],"representation.":[102],"We":[103,145],"address":[104],"shortcoming":[106],"by":[107],"injecting":[108],"lexical":[109],"information":[110],"into":[111],"using":[115],"as":[119],"teacher.":[121],"To":[122],"improve":[123],"our":[127],"approach,":[128],"propose":[130],"novel":[132],"estimate":[133],"quality":[136],"predictions,":[140,164],"condition":[142],"teacher-student":[143],"training.":[144],"report":[146],"new":[147],"audio-only":[148],"state-of-the-art":[149,172],"concordance":[150],"correlation":[151],"coefficient":[152],"(CCC)":[153],"values":[154,173],"0.757,":[156],"0.627,":[157],"0.671":[158],"activation,":[160],"respectively,":[165],"MSP-Podcast":[168],"corpus,":[169],"0.667,":[175],"0.582,":[176],"0.545":[177],"IEMOCAP":[180],"corpus.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}