{"id":"https://openalex.org/W4408352080","doi":"https://doi.org/10.1109/icassp49660.2025.10889582","title":"ITMO language diarization and identification systems for the DISPLACE 2024 challenge","display_name":"ITMO language diarization and identification systems for the DISPLACE 2024 challenge","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352080","doi":"https://doi.org/10.1109/icassp49660.2025.10889582"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5116594283","display_name":"Egor Ausev","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Egor Ausev","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084186518","display_name":"Vladimir Volokhov","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vladimir Volokhov","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109435545","display_name":"Sergey Novoselov","orcid":"https://orcid.org/0009-0009-9354-8967"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Novoselov","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594284","display_name":"Vladislav Marchevskiy","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vladislav Marchevskiy","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013759951","display_name":"\u0415. \u0418. \u0428\u0430\u043d\u0433\u0438\u043d\u0430","orcid":"https://orcid.org/0000-0001-5433-8400"},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ekaterina Shangina","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004827808","display_name":"\u0410. \u041d. \u041b\u043e\u0433\u0443\u043d\u043e\u0432","orcid":null},"institutions":[{"id":"https://openalex.org/I173089394","display_name":"ITMO University","ror":"https://ror.org/04txgxn49","country_code":"RU","type":"education","lineage":["https://openalex.org/I173089394"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexey Logunov","raw_affiliation_strings":["ITMO University,St. Petersburg,Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ITMO University,St. Petersburg,Russia","institution_ids":["https://openalex.org/I173089394"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I173089394"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01636204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9718999862670898,"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":0.9718999862670898,"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":0.9526000022888184,"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/identification","display_name":"Identification (biology)","score":0.7248976826667786},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7131228446960449},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.46711811423301697},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4612383544445038},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.41584837436676025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3608441948890686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36032769083976746},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32759666442871094},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.17906704545021057},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.051849156618118286}],"concepts":[{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7248976826667786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131228446960449},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.46711811423301697},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4612383544445038},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.41584837436676025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3608441948890686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36032769083976746},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32759666442871094},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.17906704545021057},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.051849156618118286},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2002165149","https://openalex.org/W2933138175","https://openalex.org/W2963576203","https://openalex.org/W2969985801","https://openalex.org/W3008849579","https://openalex.org/W3025515949","https://openalex.org/W3035693354","https://openalex.org/W3139878283","https://openalex.org/W3203417382","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4283067018","https://openalex.org/W4385822615","https://openalex.org/W4385823248","https://openalex.org/W4396830593","https://openalex.org/W4402111364","https://openalex.org/W6688816777","https://openalex.org/W6780218876","https://openalex.org/W6847363464","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W4403618900","https://openalex.org/W2410566519","https://openalex.org/W4318225096","https://openalex.org/W4389984014","https://openalex.org/W1585155462","https://openalex.org/W2144208207","https://openalex.org/W2972481191","https://openalex.org/W2950105263","https://openalex.org/W2166467513","https://openalex.org/W2111874347"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"language":[4,31,59,63,93,122],"diarization":[5,123],"and":[6,21,101],"identification":[7,60,86],"systems":[8],"developed":[9],"for":[10,46,65,80,118,149],"far-field":[11],"recorded":[12],"group":[13],"conversations.":[14],"Our":[15,129],"approach":[16],"has":[17],"a":[18,66],"two-stage":[19],"design":[20],"relies":[22],"on":[23,99,121,136],"classical":[24],"methods,":[25],"such":[26],"as":[27,111,113],"spectral":[28,47,81],"clustering":[29,48,82],"of":[30,69,78,124,152],"embeddings.":[32],"The":[33],"heuristic":[34],"bypass":[35],"(HBP)":[36],"method":[37],"was":[38],"utilized":[39],"to":[40,140],"generate":[41],"the":[42,51,55,58,76,85,89,125,141,146,153],"similarity":[43],"matrix":[44],"required":[45],"used":[49,108],"in":[50],"first":[52],"stage.":[53],"In":[54],"second":[56,147],"stage":[57],"block":[61,87],"predicts":[62],"labels":[64],"specific":[67],"set":[68,138],"target":[70],"languages.":[71],"Users":[72],"can":[73],"manually":[74],"determine":[75],"number":[77],"clusters":[79],"when":[83],"using":[84],"into":[88,116],"processing":[90],"pipeline.":[91],"Various":[92],"embedding":[94],"extractors,":[95],"including":[96],"those":[97],"based":[98],"ResNet34":[100],"wav2vec":[102],"2.0":[103],"architectures,":[104],"were":[105],"utilized.":[106],"We":[107],"these":[109],"systems,":[110],"well":[112],"their":[114],"fusion,":[115],"submission":[117],"Track":[119,150],"2":[120,151],"DISPLACE":[126],"2024":[127],"challenge.":[128,154],"system":[130],"achieved":[131],"5":[132],"%":[133],"relative":[134],"improvements":[135],"eval":[137],"compared":[139],"organizer-provided":[142],"baseline":[143],"system,":[144],"securing":[145],"place":[148]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
