{"id":"https://openalex.org/W4408352004","doi":"https://doi.org/10.1109/icassp49660.2025.10890558","title":"Stimulus Modality Matters: Impact of Perceptual Evaluations from Different Modalities on Speech Emotion Recognition System Performance","display_name":"Stimulus Modality Matters: Impact of Perceptual Evaluations from Different Modalities on Speech Emotion Recognition System Performance","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352004","doi":"https://doi.org/10.1109/icassp49660.2025.10890558"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5089273852","display_name":"Huang-Cheng Chou","orcid":"https://orcid.org/0000-0003-2125-5689"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huang-Cheng Chou","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Hsinchu City,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Hsinchu City,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["National Taiwan University,Department of Electrical Engineering,Taipei City,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department of Electrical Engineering,Taipei City,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086107623","display_name":"Chi-Chun Lee","orcid":"https://orcid.org/0000-0003-0186-4321"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering,Hsinchu City,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering,Hsinchu City,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7872999906539917,"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":0.7872999906539917,"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":0.7278000116348267,"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":0.6686000227928162,"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/modalities","display_name":"Modalities","score":0.7421761751174927},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.732819676399231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.686194896697998},{"id":"https://openalex.org/keywords/stimulus","display_name":"Stimulus (psychology)","score":0.6848758459091187},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6195778250694275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5860699415206909},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5362092852592468},{"id":"https://openalex.org/keywords/stimulus-modality","display_name":"Stimulus modality","score":0.4874858856201172},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3474028408527374},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3408607244491577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2754255533218384},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.18495073914527893}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7421761751174927},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.732819676399231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.686194896697998},{"id":"https://openalex.org/C2779918689","wikidata":"https://www.wikidata.org/wiki/Q3771842","display_name":"Stimulus (psychology)","level":2,"score":0.6848758459091187},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6195778250694275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5860699415206909},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5362092852592468},{"id":"https://openalex.org/C26486553","wikidata":"https://www.wikidata.org/wiki/Q371870","display_name":"Stimulus modality","level":3,"score":0.4874858856201172},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3474028408527374},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3408607244491577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2754255533218384},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.18495073914527893},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2095580536","https://openalex.org/W2101234009","https://openalex.org/W2146334809","https://openalex.org/W2313339984","https://openalex.org/W2742542661","https://openalex.org/W2798405286","https://openalex.org/W2806649730","https://openalex.org/W2963691377","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2979826702","https://openalex.org/W2982223350","https://openalex.org/W2983159143","https://openalex.org/W3015265920","https://openalex.org/W3041561163","https://openalex.org/W3097286738","https://openalex.org/W3112736871","https://openalex.org/W3172448037","https://openalex.org/W3192706046","https://openalex.org/W3197580070","https://openalex.org/W3198771897","https://openalex.org/W3198858531","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4224918091","https://openalex.org/W4297841781","https://openalex.org/W4313639160","https://openalex.org/W4361994820","https://openalex.org/W4385823105","https://openalex.org/W4387421359","https://openalex.org/W4392172995","https://openalex.org/W4399426079","https://openalex.org/W4400615821","https://openalex.org/W4406461701","https://openalex.org/W6757817989","https://openalex.org/W6769196770","https://openalex.org/W6770844057","https://openalex.org/W6780218876","https://openalex.org/W6810007534","https://openalex.org/W6810208411","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2004831463","https://openalex.org/W2110287964","https://openalex.org/W2167701463"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"systems":[4,101,114],"rely":[5],"on":[6,115,147],"speech":[7,53,63],"input":[8,65],"and":[9,110],"emotional":[10,40,59,80],"labels":[11,81,104,128,137,152],"annotated":[12],"by":[13,83,106,130,139,154],"humans.":[14],"However,":[15,42],"various":[16,116,131],"emotion":[17,47],"databases":[18],"collect":[19],"perceptional":[20],"evaluations":[21],"in":[22],"different":[23,107],"ways.":[24],"For":[25],"instance,":[26],"the":[27,43,49,58,67,75,79,87,97,112,148],"IEMOCAP":[28],"dataset":[29],"uses":[30],"video":[31],"clips":[32],"with":[33,103],"sounds":[34],"for":[35,54,90,142],"annotators":[36],"to":[37,56,70],"provide":[38],"their":[39],"perceptions.":[41],"most":[44,88],"significant":[45],"English":[46],"dataset,":[48],"MSP-PODCAST,":[50],"only":[51],"provides":[52],"raters":[55],"choose":[57],"ratings.":[60],"Nevertheless,":[61],"using":[62,136],"as":[64],"is":[66,78],"standard":[68],"approach":[69],"training":[71,91,143],"SER":[72,92,100,113],"systems.":[73,93],"Therefore,":[74],"open":[76],"question":[77],"elicited":[82,105,129,138,153],"which":[84],"scenarios":[85],"are":[86],"effective":[89],"We":[94,133],"comprehensively":[95],"compare":[96],"effectiveness":[98],"of":[99],"trained":[102],"modality":[108],"stimuli":[109,141],"evaluate":[111],"testing":[117],"conditions.":[118],"Also,":[119],"we":[120],"introduce":[121],"an":[122],"all-inclusive":[123],"label":[124],"that":[125,135],"combines":[126],"all":[127],"modalities.":[132],"show":[134],"voice-only":[140,155],"yields":[144],"better":[145],"performance":[146],"test":[149],"set,":[150],"whereas":[151],"stimuli.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
