{"id":"https://openalex.org/W4408353339","doi":"https://doi.org/10.1109/icassp49660.2025.10887715","title":"Extending Whisper for Emotion Prediction Using Word-level Pseudo Labels","display_name":"Extending Whisper for Emotion Prediction Using Word-level Pseudo Labels","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353339","doi":"https://doi.org/10.1109/icassp49660.2025.10887715"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887715","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/A5111310852","display_name":"Chin Yuen Kwok","orcid":"https://orcid.org/0000-0003-2961-552X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chin Yuen Kwok","raw_affiliation_strings":["Nanyang Technological University,Digital Trust Centre,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Digital Trust Centre,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information & Communications Technology (NICT),Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information & Communications Technology (NICT),Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941083","display_name":"Jia Qi Yip","orcid":"https://orcid.org/0000-0002-9896-9658"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jia Qi Yip","raw_affiliation_strings":["Nanyang Technological University,College of Computing and Data Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,College of Computing and Data Science,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Kyoto University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University,Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,College of Computing and Data Science,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,College of Computing and Data Science,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9182999730110168,"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":0.9182999730110168,"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":0.732427179813385},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5316698551177979},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5146742463111877},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5107669830322266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48339906334877014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47029635310173035},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13960939645767212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732427179813385},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5316698551177979},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5146742463111877},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5107669830322266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48339906334877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47029635310173035},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13960939645767212},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887715","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"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50729905","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100931502","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2786779322","https://openalex.org/W2963250244","https://openalex.org/W2972452068","https://openalex.org/W3164582967","https://openalex.org/W4386566869","https://openalex.org/W4390190597","https://openalex.org/W4392903310","https://openalex.org/W4392903618","https://openalex.org/W4392904442","https://openalex.org/W4392904444","https://openalex.org/W4392931772","https://openalex.org/W4402669711","https://openalex.org/W4403863506","https://openalex.org/W6757817989","https://openalex.org/W6771467084","https://openalex.org/W6847363464","https://openalex.org/W6857054612","https://openalex.org/W6859099255","https://openalex.org/W6859854143"],"related_works":["https://openalex.org/W1569283511","https://openalex.org/W4236193183","https://openalex.org/W2053866214","https://openalex.org/W2607505004","https://openalex.org/W2231795205","https://openalex.org/W2523632547","https://openalex.org/W3204019825","https://openalex.org/W2296205523","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"This":[0],"paper":[1],"extends":[2],"Whisper\u2019s":[3,102],"automatic":[4],"speech":[5],"recognition":[6,13],"(ASR)":[7],"capabilities":[8],"to":[9,62,66,87,115,124],"perform":[10],"speech-based":[11],"emotion":[12,18,26,49,56,73],"(SER)":[14],"by":[15],"incorporating":[16],"word-level":[17,72,77],"classification":[19,50],"alongside":[20],"ASR":[21,47,69,103],"output.":[22],"We":[23],"generate":[24,88],"four":[25],"pseudo-labels":[27],"(neutral,":[28],"happy,":[29],"sad,":[30],"angry)":[31],"for":[32,45,71],"each":[33],"word":[34,53,104],"using":[35],"a":[36],"pretrained":[37],"frame-level":[38],"SER":[39,110],"model,":[40],"and":[41,48,117],"Whisper":[42],"is":[43],"fine-tuned":[44],"joint":[46],"at":[51],"the":[52,64,68,89,96,109,118],"level.":[54],"Sentence-level":[55],"labels":[57],"are":[58,79],"masked":[59],"during":[60],"training":[61],"encourage":[63],"transformer":[65],"use":[67],"output":[70],"prediction.":[74],"During":[75],"inference,":[76],"predictions":[78,83],"combined":[80],"with":[81],"sentence-level":[82,91],"through":[84],"majority":[85],"voting":[86],"final":[90],"label.":[92],"When":[93],"evaluated":[94],"on":[95],"IEMOCAP":[97],"dataset,":[98],"our":[99],"method":[100],"maintains":[101],"error":[105],"rate":[106],"while":[107],"improving":[108],"weighted":[111],"accuracy":[112],"from":[113,122],"74.4%":[114],"76.4%":[116],"unweighted":[119],"average":[120],"recall":[121],"77.1%":[123],"79.0%.":[125]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}