{"id":"https://openalex.org/W4392903618","doi":"https://doi.org/10.1109/icassp48485.2024.10448130","title":"Foundation Model Assisted Automatic Speech Emotion Recognition: Transcribing, Annotating, and Augmenting","display_name":"Foundation Model Assisted Automatic Speech Emotion Recognition: Transcribing, Annotating, and Augmenting","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903618","doi":"https://doi.org/10.1109/icassp48485.2024.10448130"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448130","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":"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/A5100567944","display_name":"Tiantian Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tiantian Feng","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA","Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA","Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":8.89,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.98488361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12116","last_page":"12120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/annotation","display_name":"Annotation","score":0.7899476289749146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7752702236175537},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6588581204414368},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5884326100349426},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5139486193656921},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4896843731403351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47462570667266846},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43091192841529846},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4211612045764923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37575390934944153},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3688462972640991}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7899476289749146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752702236175537},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6588581204414368},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5884326100349426},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5139486193656921},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4896843731403351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47462570667266846},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43091192841529846},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4211612045764923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37575390934944153},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3688462972640991},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448130","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":37,"referenced_works":["https://openalex.org/W1973200191","https://openalex.org/W2146334809","https://openalex.org/W2342475039","https://openalex.org/W2742542661","https://openalex.org/W2962770129","https://openalex.org/W2964300796","https://openalex.org/W2965373594","https://openalex.org/W2973049979","https://openalex.org/W2979826702","https://openalex.org/W3036601975","https://openalex.org/W3163091219","https://openalex.org/W3195577433","https://openalex.org/W3197642003","https://openalex.org/W3206192140","https://openalex.org/W3208480086","https://openalex.org/W3209984917","https://openalex.org/W3212322229","https://openalex.org/W4224933334","https://openalex.org/W4235510064","https://openalex.org/W4307079201","https://openalex.org/W4311000453","https://openalex.org/W4323655724","https://openalex.org/W4367020642","https://openalex.org/W4378105483","https://openalex.org/W4384268405","https://openalex.org/W4384918448","https://openalex.org/W4385822632","https://openalex.org/W4385822836","https://openalex.org/W6766673545","https://openalex.org/W6780218876","https://openalex.org/W6800751262","https://openalex.org/W6802546489","https://openalex.org/W6847076894","https://openalex.org/W6847363464","https://openalex.org/W6852909395","https://openalex.org/W6854299349","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W235617577","https://openalex.org/W2099475353","https://openalex.org/W1966028611","https://openalex.org/W2568050604","https://openalex.org/W3195200850","https://openalex.org/W2744347949","https://openalex.org/W2048673468","https://openalex.org/W3107456284","https://openalex.org/W642007152","https://openalex.org/W3110551121"],"abstract_inverted_index":{"Significant":[0],"advances":[1],"are":[2],"being":[3],"made":[4],"in":[5,60,89,105],"speech":[6,134,144,169,175],"emotion":[7,170],"recognition":[8],"(SER)":[9],"using":[10],"deep":[11],"learning":[12,30],"models.":[13],"Nonetheless,":[14],"training":[15],"SER":[16,35,56,107,128],"systems":[17,129],"remains":[18,145],"challenging,":[19],"requiring":[20],"both":[21],"time":[22],"and":[23,43,110],"costly":[24],"resources.":[25],"Like":[26],"many":[27],"other":[28],"machine":[29],"tasks,":[31],"acquiring":[32],"datasets":[33,171],"for":[34,85],"requires":[36],"substantial":[37],"data":[38,87],"annotation":[39,46,111],"efforts,":[40],"including":[41,81],"transcription":[42,109],"labeling.":[44],"These":[45,75],"processes":[47],"present":[48],"challenges":[49],"when":[50],"attempting":[51],"to":[52,70,103,112,123],"scale":[53],"up":[54],"conventional":[55],"systems.":[57],"Recent":[58],"developments":[59],"foundational":[61,101],"models":[62,76,102,119],"have":[63,77],"had":[64],"a":[65,146],"tremendous":[66],"impact,":[67],"giving":[68],"rise":[69],"applications":[71],"such":[72],"as":[73],"ChatGPT.":[74],"enhanced":[78],"human-computer":[79],"interactions":[80],"bringing":[82],"unique":[83],"possibilities":[84],"streamlining":[86],"collection":[88],"fields":[90],"like":[91],"SER.":[92],"In":[93],"this":[94],"research,":[95],"we":[96,137],"explore":[97],"the":[98,125,156,164],"use":[99],"of":[100,127,158,166],"assist":[104],"automating":[106],"from":[108,142,152],"augmentation.":[113],"Our":[114],"study":[115],"demonstrates":[116],"that":[117,130,139],"these":[118],"can":[120],"generate":[121],"transcriptions":[122],"enhance":[124],"performance":[126],"rely":[131],"solely":[132],"on":[133],"data.":[135],"Furthermore,":[136],"note":[138],"annotating":[140,173],"emotions":[141],"transcribed":[143],"challenging":[147],"task.":[148],"However,":[149],"combining":[150],"outputs":[151],"multiple":[153],"LLMs":[154],"enhances":[155],"quality":[157],"annotations.":[159],"Lastly,":[160],"our":[161],"findings":[162],"suggest":[163],"feasibility":[165],"augmenting":[167],"existing":[168],"by":[172],"unlabeled":[174],"samples.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}