{"id":"https://openalex.org/W1992106273","doi":"https://doi.org/10.1109/tasl.2011.2160167","title":"Simultaneous Speech Detection With Spatial Features for Speaker Diarization","display_name":"Simultaneous Speech Detection With Spatial Features for Speaker Diarization","publication_year":2012,"publication_date":"2012-01-31","ids":{"openalex":"https://openalex.org/W1992106273","doi":"https://doi.org/10.1109/tasl.2011.2160167","mag":"1992106273"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2160167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2160167","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/15864","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019518554","display_name":"Martin Zelen\u00e1k","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Martin Zelenak","raw_affiliation_strings":["Department of Signal Theory and Communications, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","Dept. of Signal Theor. & Commun., Univ. Politec. de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Dept. of Signal Theor. & Commun., Univ. Politec. de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023990637","display_name":"Carlos Segura","orcid":"https://orcid.org/0000-0002-5431-5927"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Segura","raw_affiliation_strings":["Department of Signal Theory and Communications, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","Dept. of Signal Theor. & Commun., Univ. Politec. de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Dept. of Signal Theor. & Commun., Univ. Politec. de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071561412","display_name":"Jordi Luque","orcid":"https://orcid.org/0000-0002-4507-4930"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Luque","raw_affiliation_strings":["Department of Signal Theory and Communications, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","Dept. of Signal Theor. & Commun., Univ. Politec. de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Dept. of Signal Theor. & Commun., Univ. Politec. de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025633053","display_name":"Javier Hernando","orcid":"https://orcid.org/0000-0002-1730-8154"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Hernando","raw_affiliation_strings":["Department of Signal Theory and Communications, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","Dept. of Signal Theor. & Commun., Univ. Politec. de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Theory and Communications, Universitat Polilt\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Dept. of Signal Theor. & Commun., Univ. Politec. de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7153,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94985139,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"20","issue":"2","first_page":"436","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9991999864578247,"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":0.9034168720245361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7822316288948059},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7557530403137207},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6852912306785583},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.576833188533783},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5607927441596985},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5185382962226868},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5040849447250366},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4849112629890442},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4637414216995239},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4568319022655487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4170808792114258},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3814288377761841}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9034168720245361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822316288948059},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7557530403137207},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6852912306785583},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.576833188533783},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5607927441596985},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5185382962226868},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5040849447250366},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4849112629890442},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4637414216995239},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4568319022655487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4170808792114258},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3814288377761841},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2011.2160167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2160167","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/15864","is_oa":false,"landing_page_url":"https://hdl.handle.net/2117/15864","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:www.recercat.cat:2072/195970","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/15864","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:www.recercat.cat:2072/195970","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/15864","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W41021157","https://openalex.org/W43416829","https://openalex.org/W76901566","https://openalex.org/W98436420","https://openalex.org/W127975155","https://openalex.org/W148683318","https://openalex.org/W168261181","https://openalex.org/W184241528","https://openalex.org/W1524832141","https://openalex.org/W1558276682","https://openalex.org/W1603689368","https://openalex.org/W1762918658","https://openalex.org/W1946893126","https://openalex.org/W2003784299","https://openalex.org/W2069231281","https://openalex.org/W2097583714","https://openalex.org/W2098441927","https://openalex.org/W2101169486","https://openalex.org/W2114863372","https://openalex.org/W2124078061","https://openalex.org/W2130432819","https://openalex.org/W2133140216","https://openalex.org/W2134584072","https://openalex.org/W2139047213","https://openalex.org/W2140672401","https://openalex.org/W2146053319","https://openalex.org/W2148613904","https://openalex.org/W2151572725","https://openalex.org/W2155386343","https://openalex.org/W2156255174","https://openalex.org/W2159730002","https://openalex.org/W2169264834","https://openalex.org/W3129653033","https://openalex.org/W4247773827","https://openalex.org/W4285719527","https://openalex.org/W6601719842","https://openalex.org/W6606136135","https://openalex.org/W6637929209"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2206035908","https://openalex.org/W1977167953","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/W4310979479"],"abstract_inverted_index":{"Simultaneous":[0],"speech":[1,19,38],"poses":[2],"a":[3,14,131,160],"challenging":[4],"problem":[5],"for":[6,70,139],"conventional":[7],"speaker":[8,24,30,47,71,95,111],"diarization":[9,96],"systems.":[10],"In":[11,54,121],"meeting":[12,180],"data,":[13,143],"substantial":[15],"amount":[16],"of":[17,61,84,93,135,147,163],"missed":[18],"error":[20],"is":[21,34],"due":[22],"to":[23,45,113,116,159],"overlaps,":[25],"since":[26],"usually":[27],"only":[28],"one":[29],"label":[31],"per":[32],"segment":[33],"assigned.":[35],"Furthermore,":[36],"simultaneous":[37],"included":[39],"in":[40,118],"training":[41,107],"data":[42,79,173],"can":[43],"lead":[44],"corrupt":[46],"models":[48],"and":[49,108,137,141,154],"thus":[50],"worse":[51],"segmentation":[52],"performance.":[53],"this":[55],"paper,":[56],"we":[57,129],"propose":[58],"the":[59,94,99,125,164,178],"use":[60],"three":[62],"spatial":[63],"cross-correlation-based":[64],"features":[65],"together":[66],"with":[67,149,170],"spectral":[68],"information":[69],"overlap":[72,103,165],"detection":[73],"on":[74,124,177],"distant":[75],"microphones.":[76],"Different":[77],"microphone-pair":[78],"are":[80],"fused":[81],"by":[82,101],"means":[83],"principal":[85],"component":[86],"analysis.":[87],"We":[88],"have":[89],"obtained":[90],"an":[91],"improvement":[92,146,176],"system":[97],"over":[98],"baseline":[100],"discarding":[102],"segments":[104],"from":[105],"model":[106],"assigning":[109],"two":[110],"labels":[112],"them":[114],"according":[115],"likelihoods":[117],"Viterbi":[119],"decoding.":[120],"experiments":[122,169],"conducted":[123],"AMI":[126],"Meeting":[127],"corpus,":[128],"achieve":[130],"relative":[132],"DER":[133,175],"reduction":[134],"11.2%":[136],"17.0%":[138],"single-":[140],"multi-site":[142],"respectively.":[144],"The":[145],"clustering":[148],"techniques":[150],"such":[151],"as":[152,182],"beamforming":[153],"TDOA-feature":[155],"stream":[156],"also":[157],"leads":[158],"higher":[161],"effectiveness":[162],"labeling":[166],"algorithm.":[167],"Preliminary":[168],"NIST":[171],"RT":[172],"show":[174],"RT'09":[179],"recordings":[181],"well.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
