{"id":"https://openalex.org/W2103592292","doi":"https://doi.org/10.1109/icassp.2011.5947335","title":"Linguistic influences on bottom-up and top-down clustering for speaker diarization","display_name":"Linguistic influences on bottom-up and top-down clustering for speaker diarization","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2103592292","doi":"https://doi.org/10.1109/icassp.2011.5947335","mag":"2103592292"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010332658","display_name":"Simon Bozonnet","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Bozonnet","raw_affiliation_strings":["Eurecom Institute, Sophia-Antipolis, France","EURECOM, BP193, F-06904 Sophia Antipolis Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eurecom Institute, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"EURECOM, BP193, F-06904 Sophia Antipolis Cedex, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Eurecom Institute, Sophia-Antipolis, France","EURECOM, BP193, F-06904 Sophia Antipolis Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eurecom Institute, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"EURECOM, BP193, F-06904 Sophia Antipolis Cedex, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066811192","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0002-8459-1041"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":["Eurecom Institute, Sophia-Antipolis, France","EURECOM, BP193, F-06904 Sophia Antipolis Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eurecom Institute, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"EURECOM, BP193, F-06904 Sophia Antipolis Cedex, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022574838","display_name":"Rapha\u00ebl Troncy","orcid":"https://orcid.org/0000-0003-0457-1436"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Raphael Troncy","raw_affiliation_strings":["Eurecom Institute, Sophia-Antipolis, France","EURECOM, BP193, F-06904 Sophia Antipolis Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eurecom Institute, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"EURECOM, BP193, F-06904 Sophia Antipolis Cedex, France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1902872"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4625","issue":null,"first_page":"4424","last_page":"4427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9941999912261963,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9918000102043152,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8564693927764893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6884962320327759},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6370252370834351},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6347064971923828},{"id":"https://openalex.org/keywords/top-down-and-bottom-up-design","display_name":"Top-down and bottom-up design","score":0.6273465156555176},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5585736632347107},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4820895493030548},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4579748809337616},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.43099451065063477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3294353485107422},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30988943576812744},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.26181501150131226},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2129010260105133}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8564693927764893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6884962320327759},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6370252370834351},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6347064971923828},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.6273465156555176},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5585736632347107},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4820895493030548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4579748809337616},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.43099451065063477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3294353485107422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30988943576812744},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26181501150131226},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2129010260105133},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W90546637","https://openalex.org/W184672293","https://openalex.org/W1484181928","https://openalex.org/W1600395290","https://openalex.org/W2060656758","https://openalex.org/W2097470427","https://openalex.org/W2114981053","https://openalex.org/W2115130489","https://openalex.org/W2136752740","https://openalex.org/W2138730338","https://openalex.org/W2159591770","https://openalex.org/W2164512637","https://openalex.org/W2338994564","https://openalex.org/W4299586809","https://openalex.org/W6628802092","https://openalex.org/W6677131022"],"related_works":["https://openalex.org/W2386430105","https://openalex.org/W2356521405","https://openalex.org/W4389272081","https://openalex.org/W135211875","https://openalex.org/W2052269122","https://openalex.org/W2038534795","https://openalex.org/W2384358604","https://openalex.org/W1567829292","https://openalex.org/W3001063351","https://openalex.org/W4307477668"],"abstract_inverted_index":{"While":[0],"bottom-up":[1,63,92,117],"approaches":[2],"have":[3,16],"emerged":[4],"as":[5,151],"the":[6,19,45,60,79,89,124,133,156],"standard,":[7],"default":[8],"approach":[9,21],"to":[10,44,59,78,155],"clustering":[11,93,106,118],"for":[12,74,123,135],"speaker":[13,80],"diarization":[14],"we":[15],"always":[17],"found":[18],"top-down":[20,96,105],"gives":[22],"equivalent":[23],"or":[24],"superior":[25],"performance.":[26,129],"Our":[27],"recent":[28],"work":[29,131],"shows":[30],"that":[31,52,68,82,101,120,152],"significant":[32],"gains":[33],"in":[34,127],"performance":[35,56,90],"can":[36,54,71,84],"be":[37,72],"obtained":[38],"when":[39,57],"cluster":[40],"purification":[41,128],"is":[42],"applied":[43,58],"output":[46,61],"of":[47,62,91],"top":[48],"down":[49],"systems":[50],"but":[51],"it":[53],"degrade":[55],"systems.":[64],"This":[65],"paper":[66],"demonstrates":[67],"these":[69],"observations":[70],"accounted":[73],"by":[75],"factors":[76,149],"unrelated":[77],"and":[81,119],"they":[83],"impact":[85],"more":[86],"strongly":[87],"on":[88],"strategies":[94,137],"than":[95,113,146],"strategies.":[97],"Experimental":[98],"results":[99],"confirm":[100],"clusters":[102],"produced":[103,115],"through":[104,116],"are":[107],"better":[108],"normalized":[109],"against":[110],"phone":[111],"variation":[112],"those":[114,153],"this":[121],"accounts":[122],"observed":[125],"inconsistencies":[126],"The":[130],"highlights":[132],"need":[134],"marginalization":[136],"which":[138],"should":[139],"encourage":[140],"convergence":[141],"toward":[142,147],"different":[143],"speakers":[144],"rather":[145],"nuisance":[148],"such":[150],"related":[154],"linguistic":[157],"content.":[158]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}