{"id":"https://openalex.org/W4415329322","doi":"https://doi.org/10.21437/interspeech.2025-648","title":"MIKU-PAL: An Automated and Standardized Multimodal Method for Speech Paralinguistic and Affect Labeling","display_name":"MIKU-PAL: An Automated and Standardized Multimodal Method for Speech Paralinguistic and Affect Labeling","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415329322","doi":"https://doi.org/10.21437/interspeech.2025-648"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-648","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15772","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007619556","display_name":"Yifan Cheng","orcid":"https://orcid.org/0000-0003-0274-0611"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yifan Cheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103211587","display_name":"Ruoyi Zhang","orcid":"https://orcid.org/0000-0002-7941-2969"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruoyi Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101063912","display_name":"Jiatong Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007619556"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83947584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4308","last_page":"4312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9848999977111816,"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":0.9848999977111816,"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/T11448","display_name":"Face recognition and analysis","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9821000099182129,"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/paralanguage","display_name":"Paralanguage","score":0.7786999940872192},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6298999786376953},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6259999871253967},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49480000138282776},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4781999886035919},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4625000059604645},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.4255000054836273},{"id":"https://openalex.org/keywords/affective-computing","display_name":"Affective computing","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7786999940872192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283999919891357},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6298999786376953},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6259999871253967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6118999719619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5159000158309937},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4925000071525574},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C6438553","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Affective computing","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C204854418","wikidata":"https://www.wikidata.org/wiki/Q1362921","display_name":"Polling","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-648","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.15772","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15772","pdf_url":"https://arxiv.org/pdf/2505.15772","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15772","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15772","pdf_url":"https://arxiv.org/pdf/2505.15772","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1912064254","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4006316252","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G509285653","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G8300691027","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415329322.pdf","grobid_xml":"https://content.openalex.org/works/W4415329322.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Acquiring":[0],"large-scale":[1],"emotional":[2,26,119,129],"speech":[3,12,27,93,120],"data":[4],"with":[5,105],"strong":[6],"consistency":[7,66],"remains":[8],"a":[9,18,46,117,125],"challenge":[10],"for":[11,23,128],"synthesis.":[13],"This":[14],"paper":[15],"presents":[16],"MIKU-PAL,":[17,88],"fully":[19],"automated":[20],"multimodal":[21,47],"pipeline":[22],"extracting":[24],"high-consistency":[25],"from":[28,87],"unlabeled":[29],"video":[30],"data.":[31],"Leveraging":[32],"face":[33],"detection":[34],"and":[35,64,75,84,131],"tracking":[36],"algorithms,":[37],"we":[38,89,114],"developed":[39],"an":[40],"automatic":[41],"emotion":[42,94],"analysis":[43],"system":[44],"using":[45],"large":[48],"language":[49],"model":[50],"(MLLM).":[51],"Our":[52],"results":[53],"demonstrate":[54],"that":[55],"MIKU-PAL":[56],"can":[57,90],"achieve":[58],"human-level":[59],"accuracy":[60],"(68.5%":[61],"on":[62,110],"MELD)":[63],"superior":[65],"(0.93":[67],"Fleiss":[68],"kappa":[69],"score)":[70],"while":[71],"being":[72],"much":[73],"cheaper":[74],"faster":[76],"than":[77],"human":[78,103],"annotation.":[79],"With":[80],"the":[81],"high-quality,":[82],"flexible,":[83],"consistent":[85],"annotation":[86],"annotate":[91],"fine-grained":[92,118],"categories":[95],"of":[96],"up":[97],"to":[98],"26":[99],"types,":[100],"validated":[101],"by":[102],"annotators":[104],"83%":[106],"rationality":[107],"ratings.":[108],"Based":[109],"our":[111],"proposed":[112],"system,":[113],"further":[115],"released":[116],"dataset":[121],"MIKU-EmoBench(131.2":[122],"hours)":[123],"as":[124],"new":[126],"benchmark":[127],"text-to-speech":[130],"visual":[132],"voice":[133],"cloning.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-19T00:00:00"}