{"id":"https://openalex.org/W4415707156","doi":"https://doi.org/10.1109/lsp.2025.3627537","title":"When Voices Speak Louder: Leveraging Audio Signals in Emotion-Cause Extraction via Large Multilingual Multimodal Indian Dialogue Datasets","display_name":"When Voices Speak Louder: Leveraging Audio Signals in Emotion-Cause Extraction via Large Multilingual Multimodal Indian Dialogue Datasets","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415707156","doi":"https://doi.org/10.1109/lsp.2025.3627537"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3627537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3627537","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5103282328","display_name":"Nishant Kumar","orcid":"https://orcid.org/0000-0002-3553-0613"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Nishant Kumar","raw_affiliation_strings":["Indian Institute of Technology Patna, Patna, India","Indian Institute of Technology Patna, Bihar, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Indian Institute of Technology Patna, Bihar, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101702203","display_name":"Srishti Gupta","orcid":"https://orcid.org/0000-0003-1043-1296"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srishti Gupta","raw_affiliation_strings":["Indian Institute of Technology Patna, Patna, India","Indian Institute of Technology Patna, Bihar, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Indian Institute of Technology Patna, Bihar, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002025003","display_name":"Sourav Kumar Dandapat","orcid":"https://orcid.org/0000-0003-2043-2356"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sourav Kumar Dandapat","raw_affiliation_strings":["Indian Institute of Technology Patna, Patna, India","Indian Institute of Technology Patna, Bihar, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Indian Institute of Technology Patna, Bihar, India","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103282328"],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34351626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"4454","last_page":"4458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.954800009727478,"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":0.954800009727478,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.022600000724196434,"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/T12031","display_name":"Speech and dialogue systems","score":0.002400000113993883,"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/conversation","display_name":"Conversation","score":0.7627000212669373},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.6617000102996826},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4878999888896942},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46650001406669617},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4440000057220459},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3506999909877777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784600019454956},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7627000212669373},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.6617000102996826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.554099977016449},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580000042915344},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4361000061035156},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26969999074935913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3627537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3627537","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2164777277","https://openalex.org/W2342475039","https://openalex.org/W2803193013","https://openalex.org/W2963686995","https://openalex.org/W3035473672","https://openalex.org/W3037031145","https://openalex.org/W3093274101","https://openalex.org/W4281397735","https://openalex.org/W4312773554","https://openalex.org/W4385625038","https://openalex.org/W4387394061","https://openalex.org/W4389520350","https://openalex.org/W4389752793","https://openalex.org/W4392172995","https://openalex.org/W4399434529","https://openalex.org/W4401818579","https://openalex.org/W4402159674","https://openalex.org/W4404884648","https://openalex.org/W4407304142","https://openalex.org/W4407637660","https://openalex.org/W4408716096","https://openalex.org/W4411006692"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"emotion":[1,81],"and":[2,15,23,68,78,82],"cause":[3,83],"recognition":[4,84],"have":[5,25],"progressed":[6],"significantly":[7],"since":[8],"their":[9],"inception.":[10],"Existing":[11],"multimodal":[12,96],"English":[13],"datasets":[14,35,60],"newer":[16],"research":[17],"extending":[18],"to":[19,28,53,87],"languages":[20],"like":[21],"Chinese":[22],"Polish":[24],"been":[26],"developed":[27],"identify":[29],"conversation":[30],"emotion-cause":[31],"pairs.":[32],"However,":[33],"these":[34],"often":[36],"lack":[37],"cultural":[38],"relevance,":[39],"particularly":[40],"for":[41,75],"Indian":[42,97],"languages,":[43],"which":[44],"remain":[45],"underrepresented":[46],"in":[47,61,94],"the":[48,88],"field.":[49],"This":[50],"paper":[51],"aims":[52],"bridge":[54],"this":[55],"gap":[56],"by":[57],"introducing":[58],"new":[59],"India's":[62],"two":[63],"most":[64],"spoken":[65],"languages:":[66],"Hindi":[67],"Bengali.":[69],"Our":[70],"work":[71],"provides":[72],"essential":[73],"resources":[74],"more":[76],"culturally":[77],"linguistically":[79],"diverse":[80],"tasks,":[85],"contributing":[86],"broader":[89],"goal":[90],"of":[91],"enhancing":[92],"detection":[93],"multilingual,":[95],"contexts.":[98]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}
