{"id":"https://openalex.org/W4392903804","doi":"https://doi.org/10.1109/icassp48485.2024.10445740","title":"Towards Improving Speech Emotion Recognition Using Synthetic Data Augmentation from Emotion Conversion","display_name":"Towards Improving Speech Emotion Recognition Using Synthetic Data Augmentation from Emotion Conversion","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903804","doi":"https://doi.org/10.1109/icassp48485.2024.10445740"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445740","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":true,"oa_status":"green","oa_url":"https://hal.science/hal-04364976/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033550190","display_name":"Karim M. Ibrahim","orcid":"https://orcid.org/0000-0003-3315-9539"},"institutions":[{"id":"https://openalex.org/I138423393","display_name":"iRobot (United States)","ror":"https://ror.org/02ex4jy25","country_code":"US","type":"company","lineage":["https://openalex.org/I138423393"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karim M. Ibrahim","raw_affiliation_strings":["Emobot,France","Emobot (France)"],"affiliations":[{"raw_affiliation_string":"Emobot,France","institution_ids":["https://openalex.org/I138423393"]},{"raw_affiliation_string":"Emobot (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094178949","display_name":"Antony Perzo","orcid":null},"institutions":[{"id":"https://openalex.org/I138423393","display_name":"iRobot (United States)","ror":"https://ror.org/02ex4jy25","country_code":"US","type":"company","lineage":["https://openalex.org/I138423393"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antony Perzo","raw_affiliation_strings":["Emobot,France","Emobot (France)"],"affiliations":[{"raw_affiliation_string":"Emobot,France","institution_ids":["https://openalex.org/I138423393"]},{"raw_affiliation_string":"Emobot (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045593473","display_name":"Simon Leglaive","orcid":"https://orcid.org/0000-0002-8219-1298"},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Leglaive","raw_affiliation_strings":["CentraleSupélec,IETR (UMR CNRS 6164),France"],"affiliations":[{"raw_affiliation_string":"CentraleSupélec,IETR (UMR CNRS 6164),France","institution_ids":["https://openalex.org/I4210107720","https://openalex.org/I1294671590","https://openalex.org/I4210100151"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033550190"],"corresponding_institution_ids":["https://openalex.org/I138423393"],"apc_list":null,"apc_paid":null,"fwci":4.1679,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94457479,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10636","last_page":"10640"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8001492023468018},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7948470115661621},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7532899975776672},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5157039761543274},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4858410060405731},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.4245865046977997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4018971025943756},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34124284982681274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001492023468018},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7948470115661621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7532899975776672},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5157039761543274},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4858410060405731},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.4245865046977997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4018971025943756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34124284982681274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445740","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"},{"id":"pmh:oai:HAL:hal-04364976v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04364976","pdf_url":"https://hal.science/hal-04364976/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Acoustics, Speech, and Signal Processing, 2024, Seoul, South Korea. ⟨10.1109/icassp48485.2024.10445740⟩","raw_type":"Conference papers"},{"id":"pmh:oai:HAL:hal-04526999v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04526999","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04364976v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04364976","pdf_url":"https://hal.science/hal-04364976/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Acoustics, Speech, and Signal Processing, 2024, Seoul, South Korea. ⟨10.1109/icassp48485.2024.10445740⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392903804.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2069859485","https://openalex.org/W2115098197","https://openalex.org/W2146334809","https://openalex.org/W2471520273","https://openalex.org/W2602034649","https://openalex.org/W2810914326","https://openalex.org/W2962793481","https://openalex.org/W2962993399","https://openalex.org/W2963609956","https://openalex.org/W2963767194","https://openalex.org/W2972640480","https://openalex.org/W2972724712","https://openalex.org/W2975317124","https://openalex.org/W2976159681","https://openalex.org/W3010360545","https://openalex.org/W3015241559","https://openalex.org/W3034924009","https://openalex.org/W3036601975","https://openalex.org/W3081192838","https://openalex.org/W3092028330","https://openalex.org/W3139270985","https://openalex.org/W3196643119","https://openalex.org/W3197642003","https://openalex.org/W3199964822","https://openalex.org/W3209059054","https://openalex.org/W3211224152","https://openalex.org/W4297841860","https://openalex.org/W4377819254","https://openalex.org/W4385245566","https://openalex.org/W4385574033","https://openalex.org/W4394671563","https://openalex.org/W6739901393","https://openalex.org/W6753049143","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6790356757","https://openalex.org/W6803378298"],"related_works":["https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W1550318927","https://openalex.org/W4305042383","https://openalex.org/W2546649374","https://openalex.org/W2773396412","https://openalex.org/W4380854332","https://openalex.org/W2184859701","https://openalex.org/W4386232293","https://openalex.org/W4380370144"],"abstract_inverted_index":{"One":[0],"of":[1,12,59,82,99,114],"the":[2,10,57,60,74,80,84,96,112],"main":[3],"challenges":[4],"in":[5,18,111],"speech":[6,19,39,50,62,86],"emotion":[7,40,51,100,119],"recognition":[8,52,101,120],"is":[9],"lack":[11],"large":[13],"labelled":[14],"datasets.":[15],"The":[16],"progress":[17],"synthesis":[20],"allows":[21],"us":[22],"to":[23,43,69],"generate":[24,44],"reliable":[25],"and":[26,108,117],"realistic":[27],"expressive":[28],"speech.":[29],"In":[30],"this":[31,93],"work,":[32],"we":[33,78],"propose":[34],"using":[35,83,121],"a":[36,122],"state-of-the-art":[37],"end-to-end":[38],"conversion":[41],"model":[42],"new":[45,64],"synthetic":[46],"data":[47,88],"for":[48],"training":[49,75],"models.":[53],"We":[54,90],"first":[55],"evaluate":[56],"quality":[58],"converted":[61],"on":[63,71,103],"unseen":[65],"datasets,":[66,106],"which":[67],"proves":[68],"be":[70],"par":[72],"with":[73],"data.":[76],"Then,":[77],"study":[79],"effect":[81],"synthesized":[85],"as":[87],"augmentation.":[89],"show":[91],"that":[92],"approach":[94],"improves":[95],"overall":[97],"performance":[98],"models":[102],"two":[104],"different":[105],"IEMOCAP":[107],"RAVDESS,":[109],"both":[110],"cases":[113],"speaker":[115],"dependent":[116],"independent":[118],"fine-tuned":[123],"wav2vec":[124],"2.0.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}