{"id":"https://openalex.org/W2289985966","doi":"https://doi.org/10.21437/interspeech.2011-383","title":"Exploiting intra-conversation variability for speaker diarization","display_name":"Exploiting intra-conversation variability for speaker diarization","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2289985966","doi":"https://doi.org/10.21437/interspeech.2011-383","mag":"2289985966"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-383","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5051278718","display_name":"Stephen Shum","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Shum","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030009288","display_name":"Ekapol Chuangsuwanich","orcid":"https://orcid.org/0000-0001-6104-4857"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ekapol Chuangsuwanich","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112042504","display_name":"Douglas A. Reynolds","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas Reynolds","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"945","last_page":"948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9940999746322632,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9706000089645386,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.845745861530304},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7989732623100281},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6927316784858704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5545347929000854},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41534921526908875},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12922856211662292},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09876155853271484}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.845745861530304},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7989732623100281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6927316784858704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5545347929000854},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41534921526908875},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12922856211662292},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09876155853271484}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-383","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.707.7978","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.707.7978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.csail.mit.edu/sshum/papers/Interspeech2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W43416829","https://openalex.org/W2000187850","https://openalex.org/W2041823554","https://openalex.org/W2115599677","https://openalex.org/W2115979064","https://openalex.org/W2121415728","https://openalex.org/W2125642021","https://openalex.org/W2140807505","https://openalex.org/W2150769028","https://openalex.org/W2159591770","https://openalex.org/W2403589179"],"related_works":["https://openalex.org/W2162158162","https://openalex.org/W1521049138","https://openalex.org/W1509309911","https://openalex.org/W2144208207","https://openalex.org/W2175373321","https://openalex.org/W2499802997","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W2128773298","https://openalex.org/W2160753975"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,34,61],"propose":[4],"a":[5,37],"new":[6],"approach":[7,16,39],"to":[8,17,30,65],"speaker":[9,18],"diariza-tion":[10],"based":[11],"on":[12,21],"the":[13,31,45,50,63,73,80],"Total":[14],"Variability":[15,47],"verifica-tion.":[19],"Drawing":[20],"previous":[22],"work":[23],"done":[24],"in":[25,44,72],"applying":[26],"factor":[27],"anal-ysis":[28],"priors":[29],"diarization":[32,74],"problem,":[33],"arrive":[35],"at":[36],"simplified":[38],"that":[40],"exploits":[41],"intra-conversation":[42],"variability":[43],"To-tal":[46],"space":[48],"through":[49],"use":[51],"of":[52,75],"Principal":[53],"Component":[54],"Analysis":[55],"(PCA).":[56],"Using":[57],"our":[58],"proposed":[59],"methods,":[60],"demonstrate":[62],"ability":[64],"achieve":[66],"state-of-the-art":[67],"performance":[68],"(0.9":[69],"%":[70],"DER)":[71],"summed-channel":[76],"telephone":[77],"data":[78],"from":[79],"NIST":[81],"2008":[82],"SRE.":[83]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
