{"id":"https://openalex.org/W4415433498","doi":"https://doi.org/10.21437/interspeech.2025-895","title":"A Hybrid Approach to Combining Role Diarization with ASR for Professional Conversations","display_name":"A Hybrid Approach to Combining Role Diarization with ASR for Professional Conversations","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433498","doi":"https://doi.org/10.21437/interspeech.2025-895"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-895","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-895","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":["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/A5103276814","display_name":"Bongjun Kim","orcid":"https://orcid.org/0000-0002-5142-0262"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bongjun Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007466","display_name":"Arindam Ghosh","orcid":"https://orcid.org/0000-0003-2426-3115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arindam Ghosh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005148508","display_name":"Mark C. Fuhs","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark C. Fuhs","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086353379","display_name":"Anurag Chowdhury","orcid":"https://orcid.org/0000-0001-8758-988X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anurag Chowdhury","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089667871","display_name":"Deblin Bagchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deblin Bagchi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053580599","display_name":"Monika Woszczyna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monika Woszczyna","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103276814"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4121,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91696942,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5243","last_page":"5247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7549999952316284,"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":0.7549999952316284,"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/T12028","display_name":"Knowledge Management and Sharing","score":0.7157999873161316,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.6786999702453613,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.3817000091075897},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3409000039100647},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.30320000648498535},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.24709999561309814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5576000213623047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46459999680519104},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.3817000091075897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35040000081062317},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31529998779296875},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2766000032424927},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.24709999561309814},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.24120000004768372}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-895","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-895","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-24T00:00:00"}
