{"id":"https://openalex.org/W4392904321","doi":"https://doi.org/10.1109/icassp48485.2024.10448505","title":"Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations","display_name":"Speech Emotion Recognition with Distilled Prosodic and Linguistic Affect Representations","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904321","doi":"https://doi.org/10.1109/icassp48485.2024.10448505"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448505","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/A5082912094","display_name":"Debaditya Shome","orcid":"https://orcid.org/0000-0001-9168-0379"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Debaditya Shome","raw_affiliation_strings":["Queen’s University,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen’s University,Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039812985","display_name":"Ali Etemad","orcid":"https://orcid.org/0000-0001-7128-0220"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ali Etemad","raw_affiliation_strings":["Queen’s University,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen’s University,Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204722609"],"apc_list":null,"apc_paid":null,"fwci":2.7221,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89590448,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11976","last_page":"11980"},"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":0.9993000030517578,"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":0.9958999752998352,"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":0.7034674882888794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6765387058258057},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.544707715511322},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5436457991600037},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5407685041427612},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5198474526405334},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4958382546901703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44875937700271606},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4372600018978119},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3994626998901367},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24114859104156494},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0881844162940979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034674882888794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6765387058258057},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.544707715511322},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5436457991600037},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5407685041427612},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5198474526405334},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4958382546901703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44875937700271606},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4372600018978119},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3994626998901367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24114859104156494},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0881844162940979},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448505","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":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"},{"id":"https://openalex.org/F4320330223","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2085662862","https://openalex.org/W2087618018","https://openalex.org/W2146334809","https://openalex.org/W2194775991","https://openalex.org/W2239141610","https://openalex.org/W2888786729","https://openalex.org/W2896457183","https://openalex.org/W3014475539","https://openalex.org/W3015489952","https://openalex.org/W3015884429","https://openalex.org/W3036601975","https://openalex.org/W3160039712","https://openalex.org/W3160183718","https://openalex.org/W3197642003","https://openalex.org/W3204087964","https://openalex.org/W3205148967","https://openalex.org/W3205428167","https://openalex.org/W3208480086","https://openalex.org/W3209059054","https://openalex.org/W3211224152","https://openalex.org/W4221162872","https://openalex.org/W4288009632","https://openalex.org/W4319777521","https://openalex.org/W4361994820","https://openalex.org/W4372260063","https://openalex.org/W4372269797","https://openalex.org/W4372270299","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"We":[0],"propose":[1],"EmoDistill,":[2],"a":[3,34,69,98],"novel":[4],"speech":[5,37],"emotion":[6,25],"recognition":[7],"(SER)":[8],"framework":[9],"that":[10,77,88],"leverages":[11],"cross-modal":[12],"knowledge":[13],"distillation":[14],"during":[15],"training":[16],"to":[17,39],"learn":[18],"strong":[19],"linguistic":[20],"and":[21,47,51,65,74,94,101,109],"prosodic":[22,52],"representations":[23],"of":[24,36,71,105,119,122],"from":[26,68],"speech.":[27],"During":[28,56],"inference,":[29],"our":[30,58,89,123],"method":[31,59,90],"only":[32],"uses":[33],"stream":[35],"signals":[38],"perform":[40],"unimodal":[41,93],"SER":[42],"thus":[43],"reducing":[44],"computation":[45],"overhead":[46],"avoiding":[48],"run-time":[49],"transcription":[50],"feature":[53],"extraction":[54],"errors.":[55],"training,":[57],"distills":[60],"information":[61],"at":[62],"both":[63],"embedding":[64],"logit":[66],"levels":[67],"pair":[70],"pre-trained":[72],"Prosodic":[73],"Linguistic":[75],"teachers":[76],"are":[78],"fine-tuned":[79],"for":[80],"SER.":[81],"Experiments":[82],"on":[83],"the":[84,117],"IEMOCAP":[85],"benchmark":[86],"demonstrate":[87,116],"outperforms":[91],"other":[92],"multimodal":[95],"techniques":[96],"by":[97],"considerable":[99],"margin,":[100],"achieves":[102],"state-of-the-art":[103],"performance":[104],"77.49%":[106],"unweighted":[107],"accuracy":[108],"78.91%":[110],"weighted":[111],"accuracy.":[112],"Detailed":[113],"ablation":[114],"studies":[115],"impact":[118],"each":[120],"component":[121],"method.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}