{"id":"https://openalex.org/W269934362","doi":"https://doi.org/10.21437/interspeech.2006-650","title":"Tracking and beamforming for multiple simultaneous speakers with probabilistic data association filters","display_name":"Tracking and beamforming for multiple simultaneous speakers with probabilistic data association filters","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W269934362","doi":"https://doi.org/10.21437/interspeech.2006-650","mag":"269934362"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-650","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5006308425","display_name":"Tobias Gehrig","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Gehrig","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002647750","display_name":"Ulrich Klee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ulrich Klee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106034394","display_name":"John McDonough","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John W. McDonough","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053319645","display_name":"Shajith Ikbal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shajith Ikbal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064051745","display_name":"Matthias W\u00f6lfel","orcid":"https://orcid.org/0000-0003-1601-5146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias W\u00f6lfel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048075735","display_name":"Christian F\u00fcgen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian F\u00fcgen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 2038","last_page":"Thu2FoP.5"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7866397500038147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.632610023021698},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5506545305252075},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.5139724612236023},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.48393136262893677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47616809606552124},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4579680263996124},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.44770103693008423},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.44047561287879944},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43043747544288635},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.41434773802757263},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34793317317962646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3382713794708252},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12571275234222412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7866397500038147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.632610023021698},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5506545305252075},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.5139724612236023},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.48393136262893677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47616809606552124},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4579680263996124},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.44770103693008423},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.44047561287879944},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43043747544288635},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.41434773802757263},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34793317317962646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3382713794708252},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12571275234222412},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2006-650","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.544.3234","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.544.3234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gehrignet.de/media/pdf/interspeech-September2006.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1492221128","https://openalex.org/W1525535255","https://openalex.org/W1965392255","https://openalex.org/W2096763807","https://openalex.org/W2100392285","https://openalex.org/W2101414012","https://openalex.org/W2113416157","https://openalex.org/W2129866629","https://openalex.org/W2159346755","https://openalex.org/W2167667767","https://openalex.org/W3187867541"],"related_works":["https://openalex.org/W2130674020","https://openalex.org/W2093748878","https://openalex.org/W2333771223","https://openalex.org/W2120056845","https://openalex.org/W1981531423","https://openalex.org/W4394861761","https://openalex.org/W2035264131","https://openalex.org/W1679012645","https://openalex.org/W1925461966","https://openalex.org/W876328409"],"abstract_inverted_index":{"In":[0,44,93,127],"prior":[1],"work,":[2,46],"we":[3,47],"developed":[4],"a":[5,37,57,64,76,85,94,128,140,183],"speaker":[6,39,106,150],"tracking":[7,107,156],"system":[8,26,108,157],"based":[9],"on":[10,99,136,172,182],"an":[11],"extended":[12],"Kalman":[13,194],"filter":[14,81],"using":[15,148],"time":[16],"delays":[17],"of":[18,69,96,130,139,186],"arrival":[19],"(TDOAs)":[20],"as":[21],"acoustic":[22,71,191],"features.":[23],"While":[24],"this":[25,45,49],"functioned":[27],"well,":[28],"its":[29],"util-ity":[30],"was":[31,40,146,176],"limited":[32],"to":[33,41,56,75,118,123,165],"scenarios":[34],"in":[35],"which":[36,62,83,145],"single":[38,184],"be":[42],"tracked.":[43],"remove":[48],"restriction":[50],"by":[51],"generalizing":[52],"the":[53,104,110,124,137,154,168,173,187],"IEKF,":[54],"first":[55],"probabilistic":[58,78],"data":[59,79],"association":[60,80],"filter,":[61,195],"in-corporates":[63],"clutter":[65],"model":[66],"for":[67,89],"rejection":[68],"spurious":[70],"events,":[72],"and":[73,101],"then":[74],"joint":[77],"(JPDAF),":[82],"maintains":[84],"separate":[86],"state":[87],"vector":[88],"each":[90],"active":[91],"speaker.":[92],"set":[95,129],"experiments":[97,134],"conducted":[98,135],"seminar":[100],"meeting":[102],"data,":[103],"JPDAF":[105,155],"reduced":[109,158],"multiple":[111],"object":[112],"track-ing":[113],"errror":[114],"from":[115,162],"20.7":[116],"%":[117,120,164,178],"14.3":[119],"with":[121],"respect":[122],"IEKF":[125],"system.":[126],"automatic":[131,149],"speech":[132,199],"recognition":[133],"output":[138,175],"64":[141],"channel":[142,185],"microphone":[143,201],"array":[144],"beam-formed":[147],"position":[151],"estimates,":[152],"applying":[153],"word":[159,169],"error":[160,170],"rate":[161,171],"67.3":[163],"66.0%.":[166],"Moreover,":[167],"beamformed":[174],"13.0":[177],"absolute":[179],"lower":[180],"than":[181],"array.":[188],"Index":[189],"Terms:":[190],"source":[192],"localization,":[193],"person":[196],"tracking,":[197],"far-field":[198],"recognition,":[200],"arrays":[202]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
