{"id":"https://openalex.org/W4284960025","doi":"https://doi.org/10.21437/interspeech.2022-957","title":"Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation","display_name":"Speech Emotion: Investigating Model Representations, Multi-Task Learning and Knowledge Distillation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4284960025","doi":"https://doi.org/10.21437/interspeech.2022-957"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-957","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-957","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020008681","display_name":"Hsiang-Yun Sherry Chien","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsiang-Yun Sherry Chien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011566414","display_name":"Vasudha Kowtha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasudha Kowtha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069401381","display_name":"Joseph Y. Cheng","orcid":"https://orcid.org/0000-0002-6559-0473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Yitan Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090375977","display_name":"Erdrin Azemi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erdrin Azemi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4715","last_page":"4719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.996999979019165,"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/T11309","display_name":"Music and Audio Processing","score":0.9951000213623047,"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":0.7884973287582397},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7210554480552673},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5605601668357849},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4715585708618164},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4174423813819885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4150583744049072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40364307165145874},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3539324402809143},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33152711391448975},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07478711009025574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884973287582397},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7210554480552673},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5605601668357849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4715585708618164},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4174423813819885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4150583744049072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40364307165145874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3539324402809143},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33152711391448975},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07478711009025574},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-957","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-957","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W129316862","https://openalex.org/W1710082047","https://openalex.org/W1966797434","https://openalex.org/W2146334809","https://openalex.org/W2165857685","https://openalex.org/W2239141610","https://openalex.org/W2292414329","https://openalex.org/W2394932179","https://openalex.org/W2401417847","https://openalex.org/W2508418541","https://openalex.org/W2742542661","https://openalex.org/W2752234108","https://openalex.org/W2767461737","https://openalex.org/W2969889150","https://openalex.org/W2972951327","https://openalex.org/W2973034847","https://openalex.org/W3004449907","https://openalex.org/W3032325810","https://openalex.org/W3036601975","https://openalex.org/W3096690837","https://openalex.org/W3113594615","https://openalex.org/W3169320628","https://openalex.org/W3197642003","https://openalex.org/W3202370288","https://openalex.org/W3206041894","https://openalex.org/W3215155711","https://openalex.org/W4221161909","https://openalex.org/W4253573210","https://openalex.org/W4285666836"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2768175398","https://openalex.org/W2344382886","https://openalex.org/W19111321","https://openalex.org/W2530481740","https://openalex.org/W2412887479","https://openalex.org/W2953684491","https://openalex.org/W2015158429","https://openalex.org/W3196817267","https://openalex.org/W2951720331"],"abstract_inverted_index":{"Estimating":[0],"dimensional":[1,196],"emotions,":[2],"such":[3],"as":[4],"activation,":[5,101],"valence":[6,37,51,68,81,102,149],"and":[7,26,103],"dominance,":[8],"from":[9,28,58,70,83,109,161],"acoustic":[10,60,84,154],"speech":[11,29,85],"signals":[12],"has":[13,41],"been":[14],"widely":[15],"explored":[16],"over":[17,177],"the":[18,34,44,63,73],"past":[19],"few":[20],"years.While":[21],"accurate":[22],"estimation":[23,52,69,82,95,150,198],"of":[24,46,75,90,128,133],"activation":[25],"dominance":[27],"seem":[30],"to":[31,79,92,152,165],"be":[32,56,113],"possible,":[33],"same":[35],"for":[36],"remains":[38],"challenging.Previous":[39],"research":[40],"shown":[42],"that":[43,131,182],"use":[45,74],"lexical":[47],"information":[48,54],"can":[49,55,66,112],"improve":[50,67,80,93],"performance.Lexical":[53],"obtained":[57],"pre-trained":[59,76,110,134,162],"models,":[61],"where":[62],"learned":[64],"representations":[65,78,91,108,167],"speech.We":[71],"investigate":[72,106],"model":[77,135,163],"signal.We":[86],"also":[87],"explore":[88],"fusion":[89,132],"emotion":[94,99,197],"across":[96,187],"all":[97],"three":[98],"dimensions:":[100],"dominance.Additionally,":[104],"we":[105],"if":[107],"models":[111,116,123],"distilled":[114],"into":[115],"trained":[117],"with":[118,124],"low-level":[119],"features,":[120],"resulting":[121],"in":[122,138,143],"a":[125,139,169],"less":[126],"number":[127],"parameters.We":[129],"show":[130],"embeddings":[136,164],"result":[137],"79%":[140],"relative":[141,170],"improvement":[142],"concordance":[144],"correlation":[145],"coefficient":[146],"(CCC)":[147],"on":[148,201],"compared":[151],"standard":[153],"feature":[155],"baseline":[156],"(mel-filterbank":[157],"energies),":[158],"while":[159],"distillation":[160],"lowerdimensional":[166],"yielded":[168],"12%":[171],"improvement.Such":[172],"performance":[173],"gains":[174],"were":[175],"observed":[176],"two":[178,202],"evaluation":[179,189,204],"sets,":[180],"indicating":[181],"our":[183],"proposed":[184],"architecture":[185],"generalizes":[186],"those":[188],"sets.We":[190],"report":[191],"new":[192],"state-of-theart":[193],"\"text-free\"":[194],"acoustic-only":[195],"CCC":[199],"values":[200],"MSP-Podcast":[203],"sets.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}