{"id":"https://openalex.org/W4412923682","doi":"https://doi.org/10.1007/978-981-96-9805-9_8","title":"Alignment Losses for End-to-End Speaker Diarization","display_name":"Alignment Losses for End-to-End Speaker Diarization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412923682","doi":"https://doi.org/10.1007/978-981-96-9805-9_8"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-96-9805-9_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-96-9805-9_8","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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":null,"display_name":"Simeng Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Simeng Shi","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","institution_ids":[]},{"raw_affiliation_string":"Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020817636","display_name":"Zhida Song","orcid":"https://orcid.org/0000-0002-4987-5962"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhida Song","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","institution_ids":[]},{"raw_affiliation_string":"Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000449705","display_name":"Zhihua Fang","orcid":"https://orcid.org/0000-0002-3018-7414"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Fang","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","institution_ids":[]},{"raw_affiliation_string":"Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008280998","display_name":"Xiaochen Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochen Guo","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","institution_ids":[]},{"raw_affiliation_string":"Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010540039","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-4723-5486"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang He","raw_affiliation_strings":["Department of Electronic Engineering, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, 100084, China","School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Signal Detection and Processing, Urumqi, 830017, China","institution_ids":[]},{"raw_affiliation_string":"Xinjiang Multimodal Information Technology Engineering Research Center, Urumqi, 830017, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010540039"],"corresponding_institution_ids":["https://openalex.org/I96908189","https://openalex.org/I99065089"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32678707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9957000017166138,"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/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.8337136507034302},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7854299545288086},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7584295272827148},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5917760133743286},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4438701868057251},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.37167343497276306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32243120670318604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337136507034302},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7854299545288086},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7584295272827148},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5917760133743286},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4438701868057251},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.37167343497276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32243120670318604}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-96-9805-9_8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-96-9805-9_8","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W119864726","https://openalex.org/W2060729502","https://openalex.org/W2150769028","https://openalex.org/W2166637769","https://openalex.org/W2171700247","https://openalex.org/W2187693774","https://openalex.org/W2696967604","https://openalex.org/W2767895109","https://openalex.org/W2890964092","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3095212884","https://openalex.org/W3178462146","https://openalex.org/W3196857193","https://openalex.org/W3206479921","https://openalex.org/W4375869365","https://openalex.org/W6603625323"],"related_works":["https://openalex.org/W2206035908","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","https://openalex.org/W2140022733","https://openalex.org/W2911612049"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
