{"id":"https://openalex.org/W2039765984","doi":"https://doi.org/10.1109/globalsip.2014.7032178","title":"Improving overlapping speaker detection using multiple speaker tracking information","display_name":"Improving overlapping speaker detection using multiple speaker tracking information","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2039765984","doi":"https://doi.org/10.1109/globalsip.2014.7032178","mag":"2039765984"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2014.7032178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-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/A5014456106","display_name":"Youssef Oualil","orcid":"https://orcid.org/0009-0002-8528-3339"},"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":true,"raw_author_name":"Youssef Oualil","raw_affiliation_strings":["Spoken Language Systems, Saarland University, Saarbruckcn, Germany","Spoken Language Systems, Saarland University, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Spoken Language Systems, Saarland University, Saarbruckcn, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Spoken Language Systems, Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088543997","display_name":"Rahil Mahdian Toroghi","orcid":"https://orcid.org/0000-0002-7668-7369"},"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":"Rahil Mahdian Toroghi","raw_affiliation_strings":["Spoken Language Systems, Saarland University, Saarbruckcn, Germany","Spoken Language Systems, Saarland University, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Spoken Language Systems, Saarland University, Saarbruckcn, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Spoken Language Systems, Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008875255","display_name":"Dietrich Klakow","orcid":"https://orcid.org/0000-0002-4147-9690"},"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":"Dietrich Klakow","raw_affiliation_strings":["Spoken Language Systems, Saarland University, Saarbruckcn, Germany","Spoken Language Systems, Saarland University, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Spoken Language Systems, Saarland University, Saarbruckcn, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Spoken Language Systems, Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014456106"],"corresponding_institution_ids":["https://openalex.org/I91712215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10960648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"552","last_page":"556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983000159263611,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.758692741394043},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.7217345833778381},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6884180903434753},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.536620020866394},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5148093104362488},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5131133794784546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5101757049560547},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48769959807395935},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45677489042282104},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4521907567977905},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43189701437950134},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.42360424995422363},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36336779594421387},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.323490709066391},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3174413740634918},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09190142154693604},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0682726502418518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758692741394043},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.7217345833778381},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6884180903434753},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.536620020866394},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5148093104362488},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5131133794784546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5101757049560547},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48769959807395935},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45677489042282104},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4521907567977905},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43189701437950134},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.42360424995422363},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36336779594421387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.323490709066391},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3174413740634918},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09190142154693604},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0682726502418518},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip.2014.7032178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W112708033","https://openalex.org/W126779258","https://openalex.org/W1480200527","https://openalex.org/W1530327454","https://openalex.org/W1574312318","https://openalex.org/W1648602279","https://openalex.org/W2005928210","https://openalex.org/W2039760476","https://openalex.org/W2046317813","https://openalex.org/W2069748678","https://openalex.org/W2081074144","https://openalex.org/W2095940391","https://openalex.org/W2101206777","https://openalex.org/W2129078811","https://openalex.org/W2149197198","https://openalex.org/W2155544162","https://openalex.org/W2156255174","https://openalex.org/W2159346755","https://openalex.org/W2160337655","https://openalex.org/W2166320821","https://openalex.org/W2167179555","https://openalex.org/W2400585093","https://openalex.org/W2407223683","https://openalex.org/W2571050459","https://openalex.org/W3107934168","https://openalex.org/W3187867541","https://openalex.org/W4285719527","https://openalex.org/W6604630714","https://openalex.org/W6605165268","https://openalex.org/W6628719647","https://openalex.org/W6631733034","https://openalex.org/W6634207956","https://openalex.org/W6636810956","https://openalex.org/W6660116039","https://openalex.org/W6683191925","https://openalex.org/W6683575294","https://openalex.org/W6684492989","https://openalex.org/W6713688589"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Traditionally,":[0],"multiple":[1,18,88,143],"speaker":[2,65,89,144],"tracking":[3,20,32,94,132,145],"consists":[4],"of":[5,11,44,111,128],"two":[6,25,104],"stages,":[7,105],"namely,":[8],"1)":[9],"detection":[10,40,109,130],"location":[12],"measurements,":[13],"followed":[14],"by":[15],"2)":[16],"a":[17,125,141],"object":[19],"approach.":[21],"In":[22,96],"general,":[23],"these":[24],"steps":[26],"are":[27],"performed":[28],"separately,":[29],"and":[30,106,131],"the":[31,38,45,58,63,68,81,87,93,103,108,121,129,135],"performance":[33,43],"is":[34,138],"highly":[35],"dependent":[36],"on":[37,120],"measurement":[39,52,84],"rate.":[41],"The":[42],"widely":[46],"used":[47],"Steered":[48],"Response":[49],"Power":[50],"(SRP)-based":[51],"detectors,":[53],"however,":[54],"drastically":[55],"decreases":[56],"in":[57,92],"overlapping":[59,115],"speech":[60,116],"scenario,":[61],"where":[62],"dominant":[64],"frequently":[66],"masks":[67],"low-energy":[69,112],"speakers.":[70],"To":[71],"overcome":[72],"this":[73,99],"problem,":[74],"we":[75],"propose":[76],"an":[77],"approach":[78,100,137],"that":[79],"enhances":[80],"probabilistic":[82],"SRP-based":[83],"detector,":[85],"using":[86],"information":[90],"obtained":[91],"step.":[95],"doing":[97],"so,":[98],"tightly":[101],"couples":[102],"increases":[107],"rate":[110],"speakers":[113],"during":[114],"segments.":[117],"Experiments":[118],"conducted":[119],"AV16.3":[122],"corpus":[123],"showed":[124],"significant":[126],"improvement":[127],"performance,":[133],"when":[134],"proposed":[136],"integrated":[139],"into":[140],"Kalman-based":[142],"framework.":[146]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}