{"id":"https://openalex.org/W4400579202","doi":"https://doi.org/10.1109/taslp.2024.3426978","title":"Implicit Self-Supervised Language Representation for Spoken Language Diarization","display_name":"Implicit Self-Supervised Language Representation for Spoken Language Diarization","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400579202","doi":"https://doi.org/10.1109/taslp.2024.3426978"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3426978","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426978","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2024.3426978","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013209021","display_name":"Jagabandhu Mishra","orcid":"https://orcid.org/0000-0003-1878-6286"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Jagabandhu Mishra","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. R. Mahadeva Prasanna","raw_affiliation_strings":["Department of Electrical Electronics and Communication Engineering, Indian Institute of Technology (IIT) Dharwad, Dharwad, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Electronics and Communication Engineering, Indian Institute of Technology (IIT) Dharwad, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013209021"],"corresponding_institution_ids":["https://openalex.org/I175532246"],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7479887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"32","issue":null,"first_page":"3393","last_page":"3407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.9965999722480774,"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/computer-science","display_name":"Computer science","score":0.758605420589447},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.6905050873756409},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5799046754837036},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5639537572860718},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5164525508880615},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5040242075920105},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4964495301246643},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45636504888534546},{"id":"https://openalex.org/keywords/intermediate-language","display_name":"Intermediate language","score":0.4533388912677765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4501304030418396},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4367426335811615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3999846875667572},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.26700031757354736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758605420589447},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.6905050873756409},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5799046754837036},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5639537572860718},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5164525508880615},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5040242075920105},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4964495301246643},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45636504888534546},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.4533388912677765},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4501304030418396},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4367426335811615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3999846875667572},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26700031757354736},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3426978","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426978","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3426978","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426978","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2015749032","https://openalex.org/W2049032416","https://openalex.org/W2074394031","https://openalex.org/W2112844139","https://openalex.org/W2786927338","https://openalex.org/W2807627734","https://openalex.org/W2895419391","https://openalex.org/W2963542740","https://openalex.org/W3008357631","https://openalex.org/W3096096173","https://openalex.org/W3137249133","https://openalex.org/W3143367551","https://openalex.org/W3180180466","https://openalex.org/W3197380209","https://openalex.org/W3198275944","https://openalex.org/W3198614662","https://openalex.org/W3200185870","https://openalex.org/W3208240190","https://openalex.org/W3212886388","https://openalex.org/W4287075881","https://openalex.org/W4289829963","https://openalex.org/W4312351234","https://openalex.org/W4328054599","https://openalex.org/W4385822606","https://openalex.org/W4385822988","https://openalex.org/W4390701483","https://openalex.org/W4399728666","https://openalex.org/W6780218876","https://openalex.org/W6784362749","https://openalex.org/W6788865824","https://openalex.org/W6798423582","https://openalex.org/W6802591457","https://openalex.org/W6859173848"],"related_works":["https://openalex.org/W1972594981","https://openalex.org/W2136542423","https://openalex.org/W2045966063","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4398173524","https://openalex.org/W4290708361","https://openalex.org/W2129812225"],"abstract_inverted_index":{"The":[0,67,99,138],"use":[1],"of":[2,104,108,129,146,181,186],"spoken":[3],"language":[4,75,86,161],"diarization":[5,43,76],"(LD)":[6],"as":[7,27,84],"a":[8,15,158,178,184],"preprocessing":[9],"system":[10],"might":[11],"be":[12,31],"essential":[13],"in":[14,61,70,106,166,190],"code-switched":[16],"(CS)":[17],"scenario.":[18],"Furthermore,":[19],"implicit":[20,28,85,101,132,160],"frameworks":[21,29,46],"are":[22,59],"preferable":[23],"to":[24,34,64,96,135,143,150,170],"explicit":[25,97],"ones,":[26],"can":[30],"easily":[32],"adapted":[33],"deal":[35],"with":[36,88,192],"low/zero":[37],"resource":[38],"languages.":[39],"Inspired":[40],"by":[41,115],"speaker":[42],"literature,":[44],"three":[45],"based":[47],"on":[48],"(a)":[49],"fixed":[50],"segmentation,":[51,54],"(b)":[52],"change-point-based":[53],"and":[55],"(c)":[56],"end-to-end":[57],"(E2E)":[58],"used":[60,165,189],"this":[62,156,167],"study":[63],"perform":[65],"LD.":[66,98],"initial":[68],"exploration":[69],"the":[71,82,117,122,127,130,144,147,171,174,193],"constructed":[72],"text-to-speech":[73],"female":[74],"(TTSF-LD)":[77],"dataset":[78],"shows,":[79],"that":[80],"using":[81,116,121],"x-vector":[83,148,172],"representation":[87,149,162,176],"appropriate":[89],"analysis":[90],"window":[91],"length":[92],"achieves,":[93],"comparable":[94],"performance":[95,103,128,139],"best":[100],"LD":[102,133],"6.4%":[105],"terms":[107],"Jaccard":[109],"error":[110],"rate":[111],"(JER)":[112],"is":[113,141,164],"achieved":[114],"E2E":[118,131,194],"framework.":[119,195],"However,":[120],"natural":[123],"Microsoft":[124],"CS":[125],"dataset,":[126],"degrades":[134],"60.4%":[136],"JER.":[137],"degradation":[140],"due":[142],"inability":[145],"capture":[151],"language-specific":[152],"traits.":[153],"To":[154],"address":[155],"shortcoming,":[157],"self-supervised":[159,175],"framework":[163],"study.":[168],"Compared":[169],"representation,":[173],"yields":[177],"relative":[179],"improvement":[180],"63.9%,":[182],"achieving":[183],"JER":[185],"21.8%":[187],"when":[188],"conjunction":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2024-07-13T00:00:00"}