{"id":"https://openalex.org/W2170951662","doi":"https://doi.org/10.1109/icassp.2012.6288838","title":"Speaker diarization of meetings based on large TDOA feature vectors","display_name":"Speaker diarization of meetings based on large TDOA feature vectors","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2170951662","doi":"https://doi.org/10.1109/icassp.2012.6288838","mag":"2170951662"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/192694","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080162701","display_name":"Deepu Vijayasenan","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Deepu Vijayasenan","raw_affiliation_strings":["Universit\u00e4t des Saarlandes, Saarbruecken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e4t des Saarlandes, Saarbruecken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061495800","display_name":"Fabio Valente","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Fabio Valente","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4625","issue":null,"first_page":"4173","last_page":"4176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9980000257492065,"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/multilateration","display_name":"Multilateration","score":0.8142430186271667},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8108927011489868},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7904192805290222},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7093582153320312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6475052833557129},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6177234053611755},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5979201793670654},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4841218888759613},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4822302758693695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4605170488357544},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42633816599845886},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.413546085357666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13252311944961548},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1025051474571228}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.8142430186271667},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8108927011489868},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7904192805290222},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7093582153320312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6475052833557129},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6177234053611755},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5979201793670654},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4841218888759613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4822302758693695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4605170488357544},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42633816599845886},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.413546085357666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13252311944961548},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1025051474571228},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2012.6288838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.644.8388","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.644.8388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2012/Vijayasenan_ICASSP_2012.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:192694","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192694","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:192694","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/192694","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W90546637","https://openalex.org/W1556474518","https://openalex.org/W1558086160","https://openalex.org/W1963976507","https://openalex.org/W2060656758","https://openalex.org/W2096465424","https://openalex.org/W2098726438","https://openalex.org/W2103723258","https://openalex.org/W2113386290","https://openalex.org/W2148613904","https://openalex.org/W2216290105","https://openalex.org/W6603701099","https://openalex.org/W6675471587"],"related_works":["https://openalex.org/W2146992157","https://openalex.org/W2078150608","https://openalex.org/W1577891482","https://openalex.org/W119794901","https://openalex.org/W1594739536","https://openalex.org/W2408222853","https://openalex.org/W2765334250","https://openalex.org/W2262333520","https://openalex.org/W2157287565","https://openalex.org/W2100982643"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,49,57,61,86,94,97,107,129],"use":[4],"of":[5,17,77,116],"large":[6,73,122],"TDOA":[7,35,123],"feature":[8,98],"vectors":[9,124],"together":[10],"with":[11,33],"acoustic":[12],"information":[13],"in":[14],"speaker":[15,74],"diarization":[16],"meetings.":[18],"TDOAs":[19],"are":[20,125],"obtained":[21],"by":[22,131],"considering":[23],"all":[24,120],"possible":[25],"microphones":[26,117],"pairs":[27,121],"and":[28,56,88],"this":[29],"approach":[30],"is":[31,44,100,110],"compared":[32,136],"conventional":[34],"features":[36],"extracted":[37],"w.r.t.":[38],"a":[39,72],"reference":[40],"channel.":[41],"The":[42],"study":[43],"carried":[45],"using":[46],"two":[47],"systems,":[48],"first":[50,87],"based":[51,59],"on":[52,60,66],"Gaussian":[53],"Mixture":[54],"Modeling":[55],"second":[58,95],"Information":[62],"Bottleneck":[63],"approach.":[64],"Results":[65],"NIST":[67],"RT06/RT07/RT09":[68],"evaluation":[69],"datasets":[70],"show":[71],"error":[75,135],"reduction":[76],"30%":[78],"relative":[79,133],"going":[80],"from":[81,89],"14.3%":[82],"to":[83,91,113,137],"10.8%":[84],"for":[85,93],"12.3%":[90],"8.2%":[92],"whenever":[96],"weighting":[99],"properly":[101],"handled.":[102],"Furthermore":[103],"results":[104],"reveal":[105],"that":[106],"IB":[108],"system":[109],"more":[111],"robust":[112],"different":[114],"number":[115],"even":[118],"when":[119],"used":[126],"thus":[127],"outperforming":[128],"HMM/GMM":[130],"25%":[132],"(8.2%":[134],"10.8%).":[138]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}