{"id":"https://openalex.org/W4416036016","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.140","title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","display_name":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036016","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.140"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.140","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.140","pdf_url":"https://aclanthology.org/2025.findings-emnlp.140.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.140.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010509940","display_name":"Weiting Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiting Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108846913","display_name":"Jiachen Lian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiachen Lian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027043104","display_name":"Paden Tomasello","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paden Tomasello","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112014270","display_name":"Philipp Koehn","orcid":"https://orcid.org/0000-0003-1565-064X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philipp Koehn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054878003","display_name":"Xutai Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xutai Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2600","last_page":"2617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.31360000371932983,"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":0.31360000371932983,"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/T11448","display_name":"Face recognition and analysis","score":0.10339999943971634,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07259999960660934,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42980000376701355},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.33480000495910645},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.33469998836517334},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2809999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6220999956130981},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.44530001282691956},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43540000915527344},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36469998955726624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2703000009059906},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2685000002384186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.140","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.140","pdf_url":"https://aclanthology.org/2025.findings-emnlp.140.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.140","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.140","pdf_url":"https://aclanthology.org/2025.findings-emnlp.140.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036016.pdf","grobid_xml":"https://content.openalex.org/works/W4416036016.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"Audio-Visual":[3],"Language":[4],"Model":[5],"(AVLM)":[6],"for":[7,74],"expressive":[8,19,44,63],"speech":[9,20,68],"generation":[10,69],"by":[11],"integrating":[12],"full-face":[13],"visual":[14,24,64],"cues":[15],"into":[16],"a":[17,72],"pre-trained":[18],"model.We":[21],"explore":[22],"multiple":[23],"encoders":[25],"and":[26,43,70],"multimodal":[27,76],"fusion":[28],"strategies":[29],"during":[30],"pre-training":[31],"to":[32],"identify":[33],"the":[34,60],"most":[35],"effective":[36],"integration":[37],"approach.Subsequent":[38],"finetuning":[39],"on":[40],"emotion":[41,57],"recognition":[42],"dialogue":[45],"tasks":[46],"yields":[47],"substantial":[48],"gains":[49],"over":[50],"speech-only":[51],"baselines":[52],"(e.g.,":[53],"+5":[54],"F1":[55],"in":[56,66],"recognition).AVLM":[58],"highlights":[59],"value":[61],"of":[62],"information":[65],"guiding":[67],"offers":[71],"foundation":[73],"end-toend":[75],"conversational":[77],"systems.":[78]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}