{"id":"https://openalex.org/W4416799101","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249312","title":"Rethinking Cross-Corpus Speech Emotion Recognition Benchmarking: are Paralinguistic Pre-Trained Representations Sufficient?","display_name":"Rethinking Cross-Corpus Speech Emotion Recognition Benchmarking: are Paralinguistic Pre-Trained Representations Sufficient?","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799101","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249312"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5076790933","display_name":"Orchid Chetia Phukan","orcid":"https://orcid.org/0000-0002-2542-8084"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Orchid Chetia Phukan","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113394151","display_name":"Mohd Mujtaba Akhtar","orcid":"https://orcid.org/0009-0000-1982-7110"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mohd Mujtaba Akhtar","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099056916","display_name":"Girish","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Girish","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014658425","display_name":"Swarup Ranjan Behera","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swarup Ranjan Behera","raw_affiliation_strings":["Independent Researcher,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078351978","display_name":"Parabattina Bhagath","orcid":null},"institutions":[{"id":"https://openalex.org/I142253595","display_name":"University B.D.T College of Engineering","ror":"https://ror.org/033dx8j94","country_code":"IN","type":"education","lineage":["https://openalex.org/I142253595"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parabattina Bhagath","raw_affiliation_strings":["L.B.R College of Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L.B.R College of Engineering,India","institution_ids":["https://openalex.org/I142253595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025920434","display_name":"Pailla Balakrishna Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I228011842","display_name":"Reliance Industries (United States)","ror":"https://ror.org/00jfs8131","country_code":"US","type":"company","lineage":["https://openalex.org/I228011842","https://openalex.org/I4210136064"]},{"id":"https://openalex.org/I4210136064","display_name":"Reliance Industries (India)","ror":"https://ror.org/04j6cfb03","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210136064"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Pailla Balakrishna Reddy","raw_affiliation_strings":["Reliance AI,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reliance AI,India","institution_ids":["https://openalex.org/I4210136064","https://openalex.org/I228011842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014100784","display_name":"Arun Balaji Buduru","orcid":"https://orcid.org/0000-0002-6267-8138"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arun Balaji Buduru","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34702817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1022","last_page":"1027"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9894999861717224,"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":0.9894999861717224,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.002300000051036477,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0012000000569969416,"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/paralanguage","display_name":"Paralanguage","score":0.9955000281333923},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4156000018119812},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.39169999957084656},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.3776000142097473},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.36059999465942383},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.28290000557899475}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9955000281333923},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4828000068664551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47999998927116394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4528999924659729},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3637000024318695},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3610999882221222},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2777716012","wikidata":"https://www.wikidata.org/wiki/Q5318389","display_name":"Dyad","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":26,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1534131679","https://openalex.org/W2030931454","https://openalex.org/W2102697000","https://openalex.org/W2603621985","https://openalex.org/W2808331624","https://openalex.org/W2890964092","https://openalex.org/W3081192838","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3206252155","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4200019258","https://openalex.org/W4224918181","https://openalex.org/W4296068413","https://openalex.org/W4312951904","https://openalex.org/W4375869379","https://openalex.org/W4385822342","https://openalex.org/W4385822494","https://openalex.org/W4392903309","https://openalex.org/W4402111500","https://openalex.org/W4402112316","https://openalex.org/W4402112352","https://openalex.org/W4402115910","https://openalex.org/W4406461701"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"benchmarks":[1],"evaluating":[2],"pre-trained":[3,15],"models":[4],"(PTMs)":[5],"for":[6,16,90],"cross-corpus":[7,42,78,92],"speech":[8,18],"emotion":[9],"recognition":[10],"(SER)":[11],"have":[12],"overlooked":[13],"PTM":[14,37],"paralinguistic":[17,31,66],"processing":[19],"(PSP),":[20],"raising":[21],"concerns":[22],"about":[23],"their":[24],"reliability,":[25],"since":[26],"SER":[27,43,79],"is":[28],"inherently":[29],"a":[30],"task.":[32],"We":[33],"hypothesize":[34],"that":[35,63],"PSP-focused":[36,75],"will":[38],"perform":[39],"better":[40],"in":[41,77],"settings.":[44],"To":[45],"test":[46],"this,":[47],"we":[48],"analyze":[49],"state-of-the-art":[50],"PTMs":[51,76,88],"representations":[52],"including":[53],"paralinguistic,":[54],"monolingual,":[55],"multilingual,":[56],"and":[57,86],"speaker":[58],"recognition.":[59],"Our":[60],"results":[61],"confirm":[62],"TRILLsson":[64],"(a":[65],"PTM)":[67],"outperforms":[68],"others,":[69],"reinforcing":[70],"the":[71],"need":[72],"to":[73],"consider":[74],"benchmarks.":[80],"This":[81],"study":[82],"enhances":[83],"benchmark":[84],"trustworthiness":[85],"guides":[87],"evaluations":[89],"reliable":[91],"SER.":[93]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}