{"id":"https://openalex.org/W4415433048","doi":"https://doi.org/10.21437/interspeech.2025-2321","title":"Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling","display_name":"Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433048","doi":"https://doi.org/10.21437/interspeech.2025-2321"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2321","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2321","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/A5113981675","display_name":"Md Asif Jalal","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Md Asif Jalal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012558214","display_name":"Luca Remaggi","orcid":"https://orcid.org/0000-0002-4133-7043"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luca Remaggi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092031214","display_name":"Vasileios Moschopoulos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasileios Moschopoulos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044320536","display_name":"Thanasis Kotsiopoulos","orcid":"https://orcid.org/0000-0001-5178-3840"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thanasis Kotsiopoulos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071287333","display_name":"Vandana Rajan","orcid":"https://orcid.org/0000-0002-2250-1688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vandana Rajan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104088631","display_name":"Karthikeyan Saravanan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karthikeyan Saravanan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087842197","display_name":"Anastasis Drosou","orcid":"https://orcid.org/0000-0003-4019-5124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anastasis Drosou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064141074","display_name":"Junho Heo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junho Heo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061876849","display_name":"Hyuk Oh","orcid":"https://orcid.org/0000-0003-3328-0558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyuk Oh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110195272","display_name":"Seokyeong Jeong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seokyeong Jeong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5113981675"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84096028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1913","last_page":"1917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9925000071525574,"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/T11309","display_name":"Music and Audio Processing","score":0.9373000264167786,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.5026000142097473},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.453900009393692},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4422000050544739},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4043999910354614},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.3808000087738037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3580000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502000093460083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5645999908447266},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5026000142097473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011000037193298},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.453900009393692},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.3808000087738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-2321","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2321","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":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-24T00:00:00"}