{"id":"https://openalex.org/W4408353872","doi":"https://doi.org/10.1109/icassp49660.2025.10890194","title":"Self-Tuning Spectral Clustering for Speaker Diarization","display_name":"Self-Tuning Spectral Clustering for Speaker Diarization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353872","doi":"https://doi.org/10.1109/icassp49660.2025.10890194"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890194","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/A5094230049","display_name":"Nikhil Raghav","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikhil Raghav","raw_affiliation_strings":["TCG CREST,Institute for Advancing Intelligence,Kolkata,India,700 091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCG CREST,Institute for Advancing Intelligence,Kolkata,India,700 091","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026076896","display_name":"Avisek Gupta","orcid":"https://orcid.org/0000-0003-3668-0047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avisek Gupta","raw_affiliation_strings":["TCG CREST,Institute for Advancing Intelligence,Kolkata,India,700 091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCG CREST,Institute for Advancing Intelligence,Kolkata,India,700 091","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079693142","display_name":"Md Sahidullah","orcid":"https://orcid.org/0000-0002-0624-2903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md Sahidullah","raw_affiliation_strings":["TCG CREST,Institute for Advancing Intelligence,Kolkata,India,700 091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCG CREST,Institute for Advancing Intelligence,Kolkata,India,700 091","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5094230053","display_name":"Swagatam Das","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swagatam Das","raw_affiliation_strings":["TCG CREST,Institute for Advancing Intelligence,Kolkata,India,700 091"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCG CREST,Institute for Advancing Intelligence,Kolkata,India,700 091","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85581594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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":0.9822999835014343,"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":0.9822999835014343,"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":0.917900025844574,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7636497020721436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7194017171859741},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6844891905784607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5465027689933777},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48826098442077637},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37639498710632324},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3202090263366699}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7636497020721436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194017171859741},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6844891905784607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5465027689933777},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48826098442077637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37639498710632324},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3202090263366699}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890194","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W90642866","https://openalex.org/W2011430131","https://openalex.org/W2081074144","https://openalex.org/W2121947440","https://openalex.org/W2125336414","https://openalex.org/W2132914434","https://openalex.org/W2144411866","https://openalex.org/W2147286925","https://openalex.org/W2150769028","https://openalex.org/W2400584454","https://openalex.org/W2610445584","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2963745998","https://openalex.org/W2997419692","https://openalex.org/W3024869864","https://openalex.org/W3137249133","https://openalex.org/W3143367551","https://openalex.org/W3196595845","https://openalex.org/W3212886388","https://openalex.org/W4214556932","https://openalex.org/W4400315096","https://openalex.org/W4402704779","https://openalex.org/W4409642414","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Spectral":[0,117],"clustering":[1,48,118],"has":[2],"proven":[3],"effective":[4],"in":[5,95],"grouping":[6],"speech":[7],"representations":[8],"for":[9,24,73],"speaker":[10],"diarization":[11],"tasks,":[12],"although":[13],"post-processing":[14],"the":[15,22,29,71,78,85,99,106,112,123,129,135,140],"affinity":[16,44,52,86,101],"matrix":[17,45,53],"remains":[18],"difficult":[19],"due":[20],"to":[21,40],"need":[23,72],"careful":[25],"tuning":[26,75],"before":[27],"constructing":[28],"Laplacian.":[30],"In":[31],"this":[32],"study,":[33],"we":[34],"present":[35],"a":[36,42,65],"novel":[37],"pruning":[38,79],"algorithm":[39],"create":[41],"sparse":[43],"called":[46],"spectral":[47],"on":[49,58,134],"p-neighborhood":[50],"retained":[51],"(SC-pNA).":[54],"Our":[55,154],"method":[56],"improves":[57],"node-specific":[59],"fixed":[60],"neighbor":[61],"selection":[62],"by":[63,91],"allowing":[64],"variable":[66],"number":[67,124],"of":[68,98,125,142],"neighbors,":[69],"eliminating":[70],"external":[74],"data":[76],"as":[77,128],"parameters":[80],"are":[81,156],"derived":[82],"directly":[83],"from":[84,111],"matrix.":[87],"SC-pNA":[88],"does":[89],"so":[90],"identifying":[92],"two":[93],"clusters":[94,126],"every":[96],"row":[97],"initial":[100],"matrix,":[102],"and":[103],"retains":[104],"only":[105],"top":[107],"p%":[108],"similarity":[109],"scores":[110],"cluster":[113],"containing":[114],"larger":[115],"similarities.":[116],"is":[119,145],"performed":[120],"subsequently,":[121],"with":[122],"determined":[127],"maximum":[130],"eigengap.":[131],"Experimental":[132],"results":[133],"challenging":[136],"DIHARD-III":[137],"dataset":[138],"highlight":[139],"superiority":[141],"SC-pNA,":[143],"which":[144],"also":[146],"computationally":[147],"more":[148],"efficient":[149],"than":[150],"existing":[151],"auto-tuning":[152],"approaches.":[153],"implementations":[155],"available":[157],"at":[158],"https://github.com/nikhilraghav29/SC-pNA.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}