{"id":"https://openalex.org/W7148507375","doi":"https://doi.org/10.1109/asru65441.2025.11434699","title":"Utilizing Kolmogorov-Arnold Network in Self-Supervised Learning for Speaker Diarization","display_name":"Utilizing Kolmogorov-Arnold Network in Self-Supervised Learning for Speaker Diarization","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148507375","doi":"https://doi.org/10.1109/asru65441.2025.11434699"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132820810","display_name":"Minh Vu","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Minh Vu","raw_affiliation_strings":["Hanoi University of Science and Technology,SoICT,Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,SoICT,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114218708","display_name":"Phuong Tuan Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I94518387","display_name":"Hanoi University of Science and Technology","ror":"https://ror.org/04nyv3z04","country_code":"VN","type":"education","lineage":["https://openalex.org/I94518387"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phuong Tuan Dat","raw_affiliation_strings":["Hanoi University of Science and Technology,SoICT,Vietnam"],"affiliations":[{"raw_affiliation_string":"Hanoi University of Science and Technology,SoICT,Vietnam","institution_ids":["https://openalex.org/I94518387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044142616","display_name":"Kah Kuan Teh","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kah Kuan Teh","raw_affiliation_strings":["Institute for Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109364175","display_name":"Van Tuan Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Van Tuan Nguyen","raw_affiliation_strings":["Institute for Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132792742","display_name":"Tran Huy Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tran Huy Dat","raw_affiliation_strings":["Institute for Infocomm Research (I2R), A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5132820810"],"corresponding_institution_ids":["https://openalex.org/I94518387"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87573807,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8173999786376953,"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":0.8173999786376953,"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/T10320","display_name":"Neural Networks and Applications","score":0.04800000041723251,"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/T10057","display_name":"Face and Expression Recognition","score":0.007899999618530273,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.3582000136375427},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32829999923706055},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3206999897956848},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3021000027656555},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.29010000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251000165939331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4934999942779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43799999356269836},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.24740000069141388},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2459000051021576}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4733370542526245,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2107699930","https://openalex.org/W2158703410","https://openalex.org/W2808631503","https://openalex.org/W2972949456","https://openalex.org/W2995181338","https://openalex.org/W3008357631","https://openalex.org/W3095212884","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3157070662","https://openalex.org/W3163903701","https://openalex.org/W3196117288","https://openalex.org/W3196857193","https://openalex.org/W3197580070","https://openalex.org/W3198694222","https://openalex.org/W3207834622","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3212886388","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4396878152","https://openalex.org/W4400615784","https://openalex.org/W4402111989","https://openalex.org/W4405936758","https://openalex.org/W4408352169","https://openalex.org/W4411095744","https://openalex.org/W4417268310"],"related_works":[],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,107],"is":[2],"essential":[3],"in":[4,33,121],"speech":[5],"processing":[6],"but":[7],"remains":[8],"difficult":[9],"due":[10],"to":[11],"challenges":[12],"like":[13],"background":[14],"noise,":[15],"far-field":[16],"audio,":[17],"overlapping":[18],"speech,":[19],"and":[20,112],"unknown":[21],"numbers":[22],"of":[23,75,84,119],"speakers.":[24],"Self-supervised":[25],"learning":[26,124],"(SSL)":[27],"has":[28],"recently":[29],"shown":[30],"strong":[31],"performance":[32],"neural":[34],"speaker":[35,127],"segmentation":[36],"(NSS),":[37],"typically":[38],"using":[39],"pre-trained":[40],"models":[41],"with":[42,66],"Transformer":[43],"or":[44],"Conformer":[45],"decoders":[46],"connected":[47],"via":[48],"a":[49,67],"Multi-Layer":[50],"Perceptron":[51],"(MLP)":[52],"adapter.":[53],"In":[54],"this":[55],"work,":[56],"we":[57],"enhance":[58],"the":[59,64,82,117],"WavLM-Conformer":[60],"architecture":[61],"by":[62],"replacing":[63],"MLP":[65],"Kolmogorov-Arnold":[68],"Network":[69],"(KAN),":[70],"which":[71],"offers":[72],"better":[73],"approximation":[74],"multivariate":[76],"functions.":[77],"Our":[78],"KAN-based":[79],"adapter":[80],"improves":[81],"integration":[83],"SSL":[85],"features":[86],"into":[87],"downstream":[88],"tasks.":[89],"Experiments":[90],"show":[91],"that":[92],"our":[93],"model":[94],"achieves":[95],"consistent":[96],"gains":[97],"over":[98],"existing":[99],"approaches,":[100],"setting":[101],"new":[102],"state-of-the-art":[103],"results":[104,115],"on":[105],"challenging":[106],"benchmarks":[108],"such":[109],"as":[110],"AMI":[111],"AISHELL-4.":[113],"These":[114],"demonstrate":[116],"promise":[118],"KANs":[120],"advancing":[122],"deep":[123],"architectures":[125],"for":[126],"diarization.":[128]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}