{"id":"https://openalex.org/W2093499222","doi":"https://doi.org/10.1109/taslp.2013.2285474","title":"A Study of the Cosine Distance-Based Mean Shift for Telephone Speech Diarization","display_name":"A Study of the Cosine Distance-Based Mean Shift for Telephone Speech Diarization","publication_year":2013,"publication_date":"2013-12-04","ids":{"openalex":"https://openalex.org/W2093499222","doi":"https://doi.org/10.1109/taslp.2013.2285474","mag":"2093499222"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2013.2285474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2013.2285474","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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054939121","display_name":"Mohammed Senoussaoui","orcid":"https://orcid.org/0000-0002-5552-7120"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]},{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohammed Senoussaoui","raw_affiliation_strings":["\u00c9cole de technologie sup\u00e9rieure (\u00c9TS), Montr\u00e9al, QC, Canada","Centre de Rech. Inf. de Montreal (CRIM), Montre\u0301al, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole de technologie sup\u00e9rieure (\u00c9TS), Montr\u00e9al, QC, Canada","institution_ids":["https://openalex.org/I9736820"]},{"raw_affiliation_string":"Centre de Rech. Inf. de Montreal (CRIM), Montre\u0301al, QC, Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036466893","display_name":"Patrick Kenny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Patrick Kenny","raw_affiliation_strings":["Centre de recherche informatique de Montr\u00e9al (CRIM), Montr\u00e9al, QC, Canada","Centre de Rech. Inf. de Montreal (CRIM), Montre\u0301al, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre de recherche informatique de Montr\u00e9al (CRIM), Montr\u00e9al, QC, Canada","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"Centre de Rech. Inf. de Montreal (CRIM), Montre\u0301al, QC, Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Centre de recherche informatique de Montr\u00e9al (CRIM), Montr\u00e9al, QC, Canada","Centre de Rech. Inf. de Montreal (CRIM), Montre\u0301al, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre de recherche informatique de Montr\u00e9al (CRIM), Montr\u00e9al, QC, Canada","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"Centre de Rech. Inf. de Montreal (CRIM), Montre\u0301al, QC, Canada","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034083532","display_name":"Pierre Dumouchel","orcid":"https://orcid.org/0000-0001-5584-4428"},"institutions":[{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]},{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA","FR"],"is_corresponding":false,"raw_author_name":"Pierre Dumouchel","raw_affiliation_strings":["\u00c9cole de technologie sup\u00e9rieure (\u00c9TS), Montr\u00e9al, QC, Canada","Ecole de Technol. Super. (ETS), Montre\u0301al, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole de technologie sup\u00e9rieure (\u00c9TS), Montr\u00e9al, QC, Canada","institution_ids":["https://openalex.org/I9736820"]},{"raw_affiliation_string":"Ecole de Technol. Super. (ETS), Montre\u0301al, QC, Canada","institution_ids":["https://openalex.org/I29607241","https://openalex.org/I9736820"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.7299,"has_fulltext":false,"cited_by_count":172,"citation_normalized_percentile":{"value":0.97875289,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"22","issue":"1","first_page":"217","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.995199978351593,"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":0.7514273524284363},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7366539239883423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7274013161659241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6432756781578064},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5904799103736877},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.54767906665802},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3315905034542084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27932044863700867}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7514273524284363},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7366539239883423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7274013161659241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6432756781578064},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5904799103736877},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.54767906665802},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3315905034542084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27932044863700867}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2013.2285474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2013.2285474","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:espace2.etsmtl.ca:6446","is_oa":false,"landing_page_url":"https://espace2.etsmtl.ca/id/eprint/6446/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402392","display_name":"Espace \u00c9TS (ETS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1341030882","host_organization_name":"Educational Testing Service","host_organization_lineage":["https://openalex.org/I1341030882"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article publi\u00e9 dans une revue, r\u00e9vis\u00e9 par les pairs"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W36432376","https://openalex.org/W204053250","https://openalex.org/W1482583861","https://openalex.org/W1568065815","https://openalex.org/W1991422884","https://openalex.org/W2022686119","https://openalex.org/W2029687556","https://openalex.org/W2049633694","https://openalex.org/W2064364374","https://openalex.org/W2067191022","https://openalex.org/W2089542572","https://openalex.org/W2107617395","https://openalex.org/W2115599677","https://openalex.org/W2117658559","https://openalex.org/W2121415728","https://openalex.org/W2125642021","https://openalex.org/W2132103241","https://openalex.org/W2140807505","https://openalex.org/W2148374980","https://openalex.org/W2149107824","https://openalex.org/W2150769028","https://openalex.org/W2161710584","https://openalex.org/W2164500538","https://openalex.org/W2168175751","https://openalex.org/W2189248916","https://openalex.org/W2289985966","https://openalex.org/W2340176088","https://openalex.org/W2395371365","https://openalex.org/W2395750323","https://openalex.org/W2398362606","https://openalex.org/W2398928324","https://openalex.org/W2400584454","https://openalex.org/W2407374891","https://openalex.org/W2408021097","https://openalex.org/W4285719527","https://openalex.org/W6676027155","https://openalex.org/W6712009160","https://openalex.org/W6712660717","https://openalex.org/W6712796495","https://openalex.org/W6714259624"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W1556857061"],"abstract_inverted_index":{"Speaker":[0],"clustering":[1,59],"is":[2],"a":[3,45],"crucial":[4],"step":[5],"for":[6],"speaker":[7,58],"diarization.":[8],"The":[9],"short":[10],"duration":[11],"of":[12,22,28,34,65,81,95],"speech":[13,17,41],"segments":[14],"in":[15,37,73],"telephone":[16,40,102],"dialogue":[18],"and":[19,92],"the":[20,26,32,53,66,82,88,93,99],"absence":[21],"prior":[23],"information":[24],"on":[25,52,98],"number":[27],"clusters":[29],"dramatically":[30],"increase":[31],"difficulty":[33],"this":[35],"problem":[36],"diarizing":[38],"spontaneous":[39],"conversations.":[42],"We":[43,78],"propose":[44],"simple":[46],"iterative":[47],"Mean":[48,69],"Shift":[49,70],"algorithm":[50],"based":[51],"cosine":[54,67],"distance":[55,68],"to":[56],"perform":[57],"under":[60],"these":[61],"conditions.":[62],"Two":[63],"variants":[64],"are":[71],"compared":[72],"an":[74],"exhaustive":[75],"practical":[76],"study.":[77],"report":[79],"state":[80],"art":[83],"results":[84],"as":[85],"measured":[86],"by":[87],"Diarization":[89],"Error":[90],"Rate":[91],"Number":[94],"Detected":[96],"Speakers":[97],"LDC":[100],"CallHome":[101],"corpus.":[103]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}