{"id":"https://openalex.org/W4415432662","doi":"https://doi.org/10.21437/interspeech.2025-2648","title":"Overlap-Adaptive Hybrid Speaker Diarization and ASR-Aware Observation Addition for MISP 2025 Challenge","display_name":"Overlap-Adaptive Hybrid Speaker Diarization and ASR-Aware Observation Addition for MISP 2025 Challenge","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432662","doi":"https://doi.org/10.21437/interspeech.2025-2648"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2648","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2648","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/A5113335993","display_name":"Shangkun Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shangkun Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011431550","display_name":"Yuxuan Du","orcid":"https://orcid.org/0000-0002-5997-7882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102753054","display_name":"Jingwen Yang","orcid":"https://orcid.org/0000-0002-6314-3856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingwen Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024748224","display_name":"Dejun Zhang","orcid":"https://orcid.org/0000-0003-0951-9637"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dejun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046221437","display_name":"Xupeng Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xupeng Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727973","display_name":"Jing Deng","orcid":"https://orcid.org/0000-0003-4032-0482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071873783","display_name":"Jintao Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jintao Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056442083","display_name":"Rong Zheng","orcid":"https://orcid.org/0000-0003-4070-075X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89105603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1908","last_page":"1912"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9901000261306763,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9901000261306763,"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":0.38100001215934753},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.28279998898506165},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.26750001311302185},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.2646999955177307},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26089999079704285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5727999806404114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5002999901771545},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.38100001215934753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2484000027179718},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.21570000052452087}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-2648","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2648","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":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}