{"id":"https://openalex.org/W4416504048","doi":"https://doi.org/10.1186/s13636-025-00431-4","title":"Speaker embedding loss for end-to-end speaker diarization without external embedding networks","display_name":"Speaker embedding loss for end-to-end speaker diarization without external embedding networks","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W4416504048","doi":"https://doi.org/10.1186/s13636-025-00431-4"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00431-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00431-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00431-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00431-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074949149","display_name":"Jaehee Jung","orcid":"https://orcid.org/0000-0002-0932-3039"},"institutions":[{"id":"https://openalex.org/I146429904","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935","country_code":"KR","type":"education","lineage":["https://openalex.org/I146429904"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehee Jung","raw_affiliation_strings":["Department of Computer Science and Engineering, Incheon National University, 119 Academy-ro, 22012, Yeonsu-gu, Incheon, Republic of Korea","Human-Centered Artificial Intelligence Research Center, Incheon National University, 22012, Incheon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Incheon National University, 119 Academy-ro, 22012, Yeonsu-gu, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I146429904"]},{"raw_affiliation_string":"Human-Centered Artificial Intelligence Research Center, Incheon National University, 22012, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I146429904"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101977970","display_name":"Wooil Kim","orcid":"https://orcid.org/0000-0002-3854-2783"},"institutions":[{"id":"https://openalex.org/I146429904","display_name":"Incheon National University","ror":"https://ror.org/02xf7p935","country_code":"KR","type":"education","lineage":["https://openalex.org/I146429904"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wooil Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Incheon National University, 119 Academy-ro, 22012, Yeonsu-gu, Incheon, Republic of Korea","Human-Centered Artificial Intelligence Research Center, Incheon National University, 22012, Incheon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Incheon National University, 119 Academy-ro, 22012, Yeonsu-gu, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I146429904"]},{"raw_affiliation_string":"Human-Centered Artificial Intelligence Research Center, Incheon National University, 22012, Incheon, Republic of Korea","institution_ids":["https://openalex.org/I146429904"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89623827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9639000296592712,"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":0.9639000296592712,"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/T10860","display_name":"Speech and Audio Processing","score":0.011099999770522118,"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/T10028","display_name":"Topic Modeling","score":0.0019000000320374966,"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/embedding","display_name":"Embedding","score":0.8533999919891357},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7835999727249146},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6008999943733215},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.4984000027179718},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44510000944137573},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3984000086784363},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3971000015735626},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39259999990463257}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8533999919891357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991999983787537},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7835999727249146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6596999764442444},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4984000027179718},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.38420000672340393},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3831999897956848},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00431-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00431-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00431-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:99dea3d9d2a14e5bb4634244e2e05644","is_oa":true,"landing_page_url":"https://doaj.org/article/99dea3d9d2a14e5bb4634244e2e05644","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-9 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00431-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00431-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00431-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416504048.pdf","grobid_xml":"https://content.openalex.org/works/W4416504048.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1591607137","https://openalex.org/W1606894530","https://openalex.org/W2046056978","https://openalex.org/W2125336414","https://openalex.org/W2150769028","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2748488820","https://openalex.org/W2963470929","https://openalex.org/W2972680151","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3015783745","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3147778289","https://openalex.org/W3160044950","https://openalex.org/W3163903701","https://openalex.org/W3196857193","https://openalex.org/W3197916665","https://openalex.org/W4221165661","https://openalex.org/W4225661121","https://openalex.org/W4319862481","https://openalex.org/W4385573729","https://openalex.org/W4385822818","https://openalex.org/W4408054164"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,75,104,141,182],"novel":[4],"speaker":[5,22,30,53,72,133,178],"embedding":[6,31,58,88,134,179],"loss":[7,80,106,135,180],"function":[8],"designed":[9],"to":[10,84,93,107,187],"improve":[11],"the":[12,39,60,86,91,131,151,173,176],"performance":[13,159],"of":[14,71,175],"end-to-end":[15],"neural":[16],"diarization":[17,138,192],"(EEND)":[18],"systems":[19,189],"by":[20],"enhancing":[21],"discrimination.":[23],"Unlike":[24],"previous":[25],"methods":[26],"that":[27,130],"require":[28],"additional":[29],"networks":[32],"or":[33],"pre-training":[34],"on":[35,117,150],"large-scale":[36],"speaker-labeled":[37],"datasets,":[38,122],"proposed":[40,79,132,177],"approach":[41],"derives":[42],"speaker-wise":[43],"embeddings":[44,96],"directly":[45],"from":[46],"frame-level":[47],"encoder":[48],"outputs":[49],"and":[50,64,100,120,125,166,195],"ground":[51],"truth":[52],"labels.":[54],"By":[55],"avoiding":[56],"external":[57],"networks,":[59],"architecture":[61],"remains":[62],"simple":[63],"efficient":[65],"while":[66],"still":[67],"facilitating":[68],"effective":[69,185],"learning":[70],"characteristics":[73],"within":[74],"unified":[76],"framework.":[77],"The":[78,127],"incorporates":[81],"cosine":[82],"similarity":[83],"maximize":[85],"inter-speaker":[87],"distance,":[89],"encouraging":[90],"model":[92],"learn":[94],"discriminative":[95],"for":[97,190],"each":[98],"speaker,":[99],"is":[101],"integrated":[102],"with":[103],"permutation-free":[105],"resolve":[108],"label":[109],"ambiguity":[110],"during":[111],"training.":[112],"Experimental":[113],"evaluations":[114],"were":[115,161],"conducted":[116],"both":[118],"simulated":[119],"real-world":[121],"including":[123],"LibriSpeech":[124,153],"CALLHOME.":[126],"results":[128],"demonstrate":[129],"significantly":[136],"improves":[137],"accuracy,":[139],"achieving":[140],"20.8%":[142],"relative":[143],"reduction":[144],"in":[145,164,193],"Diarization":[146],"Error":[147],"Rate":[148],"(DER)":[149],"two-speaker":[152],"dataset":[154],"(4.99%":[155],"$$\\rightarrow$$":[156],"3.95%).":[157],"Consistent":[158],"gains":[160],"also":[162],"observed":[163],"five-speaker":[165],"CALLHOME":[167],"evaluation":[168],"settings.":[169],"These":[170],"findings":[171],"underscore":[172],"potential":[174],"as":[181],"lightweight":[183],"yet":[184],"addition":[186],"EEND":[188],"improved":[191],"overlapping":[194],"conversational":[196],"speech":[197],"scenarios.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-23T00:00:00"}