{"id":"https://openalex.org/W4412944939","doi":"https://doi.org/10.18653/v1/2025.acl-long.977","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization on Multi-party Conversation","display_name":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization on Multi-party Conversation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944939","doi":"https://doi.org/10.18653/v1/2025.acl-long.977"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.977","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.977","pdf_url":"https://aclanthology.org/2025.acl-long.977.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.977.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102891716","display_name":"Luyao Cheng","orcid":"https://orcid.org/0009-0006-1311-8448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luyao Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779741","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-4910-7824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100569726","display_name":"Chong Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014586639","display_name":"Siqi Zheng","orcid":"https://orcid.org/0000-0002-4467-8505"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siqi Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003578886","display_name":"Yafeng Chen","orcid":"https://orcid.org/0000-0002-5459-4428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yafeng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002111548","display_name":"Rongjie Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672350","display_name":"Qinglin Zhang","orcid":"https://orcid.org/0000-0002-3640-2883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinglin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428431","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0001-6939-7438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108913367","display_name":"Xihao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xihao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100952183","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-6545-2265"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Wang","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19914","last_page":"19928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9480999708175659,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9480999708175659,"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":0.8755291700363159},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7719122171401978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7676454782485962},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6011159420013428},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.39307624101638794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3767798840999603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32036513090133667},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.12698233127593994},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11057260632514954}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8755291700363159},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7719122171401978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676454782485962},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6011159420013428},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.39307624101638794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3767798840999603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32036513090133667},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.12698233127593994},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11057260632514954}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.977","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.977","pdf_url":"https://aclanthology.org/2025.acl-long.977.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.977","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.977","pdf_url":"https://aclanthology.org/2025.acl-long.977.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944939.pdf","grobid_xml":"https://content.openalex.org/works/W4412944939.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4389984014","https://openalex.org/W1940231550","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Luyao":[0],"Cheng,":[1],"Hui":[2],"Wang,":[3],"Chong":[4],"Deng,":[5],"Siqi":[6],"Zheng,":[7],"Yafeng":[8],"Chen,":[9,15],"Rongjie":[10],"Huang,":[11],"Qinglin":[12],"Zhang,":[13],"Qian":[14],"Xihao":[16],"Li,":[17],"Wen":[18],"Wang.":[19],"Proceedings":[20],"of":[21,26],"the":[22,27],"63rd":[23],"Annual":[24],"Meeting":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2025.":[36]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
