{"id":"https://openalex.org/W2151283590","doi":"https://doi.org/10.1109/iros.2011.6095051","title":"Multi-modal front-end for speaker activity detection in small meetings","display_name":"Multi-modal front-end for speaker activity detection in small meetings","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W2151283590","doi":"https://doi.org/10.1109/iros.2011.6095051","mag":"2151283590"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2011.6095051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2011.6095051","pdf_url":null,"source":{"id":"https://openalex.org/S4363608614","display_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5033160141","display_name":"Jani Even","orcid":"https://orcid.org/0000-0003-0743-5384"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jani Even","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029779616","display_name":"Panikos Heracleous","orcid":"https://orcid.org/0000-0002-7709-8195"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Panikos Heracleous","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000037110","display_name":"Carlos Toshinori Ishi","orcid":"https://orcid.org/0000-0001-8130-1048"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Carlos Ishi","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058513264","display_name":"Norihiro Hagita","orcid":"https://orcid.org/0000-0001-8007-4701"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Norihiro Hagita","raw_affiliation_strings":["ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Intelligent Robotics and Communication Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I4210104143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210104143"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4625","issue":null,"first_page":"536","last_page":"541"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7169958353042603},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.675873875617981},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.650809109210968},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6304485201835632},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5442940592765808},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5400193333625793},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4963083863258362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46584782004356384},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.4550025463104248},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4542858600616455},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4451269507408142},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.4389979839324951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4304657578468323},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3593391180038452},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18479695916175842},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.09882056713104248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7169958353042603},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.675873875617981},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.650809109210968},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6304485201835632},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5442940592765808},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5400193333625793},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4963083863258362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46584782004356384},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.4550025463104248},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4542858600616455},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4451269507408142},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.4389979839324951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4304657578468323},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3593391180038452},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18479695916175842},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.09882056713104248},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2011.6095051","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2011.6095051","pdf_url":null,"source":{"id":"https://openalex.org/S4363608614","display_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","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":19,"referenced_works":["https://openalex.org/W76597279","https://openalex.org/W90546637","https://openalex.org/W1876378865","https://openalex.org/W2005522781","https://openalex.org/W2023847438","https://openalex.org/W2025344720","https://openalex.org/W2060656758","https://openalex.org/W2078385108","https://openalex.org/W2083751884","https://openalex.org/W2101609516","https://openalex.org/W2114863372","https://openalex.org/W2141398670","https://openalex.org/W2149986665","https://openalex.org/W2162158162","https://openalex.org/W2163065939","https://openalex.org/W2165880886","https://openalex.org/W3147161844","https://openalex.org/W6603233860","https://openalex.org/W6684372933"],"related_works":["https://openalex.org/W2064636555","https://openalex.org/W2585503716","https://openalex.org/W1939982668","https://openalex.org/W2105014086","https://openalex.org/W2076090200","https://openalex.org/W3025682415","https://openalex.org/W2081173909","https://openalex.org/W4382317424","https://openalex.org/W4389009659","https://openalex.org/W1532481220"],"abstract_inverted_index":{"Small":[0],"informal":[1],"meetings":[2,25],"of":[3,27,46,68,71,124,141,169,187,193],"two":[4],"to":[5,32,40,43,60,90,190],"four":[6],"participants":[7,198],"are":[8,104,199],"very":[9],"common":[10],"in":[11,121],"work":[12],"environments.":[13],"For":[14],"this":[15,62],"reason,":[16],"a":[17,51,56,79,116,163],"convenient":[18],"way":[19],"for":[20,99,109,172],"recording":[21],"and":[22],"archiving":[23],"these":[24],"is":[26,42,75,96,149],"great":[28],"interest.":[29],"In":[30,112,176],"order":[31],"efficiently":[33],"archive":[34],"such":[35],"meetings,":[36],"an":[37,184],"important":[38],"task":[39],"address":[41],"keep":[44],"trace":[45],"\u201cwho":[47],"talked":[48],"when\u201d":[49],"during":[50],"meeting.":[52],"This":[53,94],"paper":[54],"proposes":[55],"new":[57],"multi-modal":[58],"approach":[59,74],"tackle":[61],"speaker":[63,146,173],"activity":[64,147,174],"detection":[65,148],"problem.":[66],"One":[67],"the":[69,72,92,113,122,125,129,133,139,142,145,167,170,178,191],"novelty":[70],"proposed":[73,114,179],"that":[76,82,155],"it":[77],"uses":[78],"human":[80,136],"tracker":[81,137],"relies":[83],"on":[84],"scanning":[85],"laser":[86],"range":[87],"finders":[88],"(LRFs)":[89],"localize":[91],"participants.":[93,143],"choice":[95],"especially":[97],"relevant":[98],"robotic":[100],"applications":[101],"as":[102],"robots":[103],"often":[105],"equipped":[106],"with":[107],"LRFs":[108],"navigation":[110],"purpose.":[111],"system,":[115],"table":[117],"top":[118],"microphone":[119,196],"array":[120],"center":[123],"meeting":[126,164],"room":[127],"acquires":[128],"audio":[130],"data":[131],"while":[132,197],"LRF":[134],"based":[135],"monitors":[138],"movement":[140],"Then":[144],"performed":[150],"using":[151],"Gaussian":[152],"mixture":[153],"models":[154],"were":[156],"trained":[157],"before":[158],"hand.":[159],"An":[160],"experiment":[161],"reproducing":[162],"configuration":[165],"demonstrates":[166],"performance":[168,188],"system":[171,182],"detection.":[175],"particular,":[177],"hands":[180],"free":[181],"maintains":[183],"good":[185],"level":[186],"compared":[189],"use":[192],"close":[194],"talking":[195],"simultaneously":[200],"speaking.":[201]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
