{"id":"https://openalex.org/W124864882","doi":"https://doi.org/10.21437/eurospeech.2001-311","title":"Real-time multiple speaker tracking by multi-modal integration for mobile robots","display_name":"Real-time multiple speaker tracking by multi-modal integration for mobile robots","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W124864882","doi":"https://doi.org/10.21437/eurospeech.2001-311","mag":"124864882"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-311","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5091708408","display_name":"Kazuhiro Nakadai","orcid":"https://orcid.org/0000-0002-6134-4558"},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["Japan Science and Technology Agency"],"affiliations":[{"raw_affiliation_string":"Japan Science and Technology Agency","institution_ids":["https://openalex.org/I4210086780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109194975","display_name":"K. Hidai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ken-ichi Hidai","raw_affiliation_strings":["Japan Science and Technology Agency"],"affiliations":[{"raw_affiliation_string":"Japan Science and Technology Agency","institution_ids":["https://openalex.org/I4210086780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086835862","display_name":"Hiroaki Kitano","orcid":"https://orcid.org/0000-0002-3589-1953"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hiroaki Kitano","raw_affiliation_strings":["Sony"],"affiliations":[{"raw_affiliation_string":"Sony","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091708408"],"corresponding_institution_ids":["https://openalex.org/I4210086780"],"apc_list":null,"apc_paid":null,"fwci":0.9351,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.74294671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1193","last_page":"1196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9872999787330627,"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":0.9872999787330627,"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/T11615","display_name":"Control and Dynamics of Mobile Robots","score":0.9704999923706055,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12031","display_name":"Speech and dialogue systems","score":0.9650999903678894,"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":0.7206054329872131},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6689750552177429},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6359593272209167},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.537125289440155},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42950135469436646},{"id":"https://openalex.org/keywords/mobile-telephony","display_name":"Mobile telephony","score":0.41173693537712097},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.38779380917549133},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3201887011528015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3144426941871643},{"id":"https://openalex.org/keywords/mobile-radio","display_name":"Mobile radio","score":0.1977086067199707},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1591334044933319}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7206054329872131},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6689750552177429},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6359593272209167},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.537125289440155},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42950135469436646},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.41173693537712097},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.38779380917549133},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3201887011528015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3144426941871643},{"id":"https://openalex.org/C2781307350","wikidata":"https://www.wikidata.org/wiki/Q6887221","display_name":"Mobile radio","level":2,"score":0.1977086067199707},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1591334044933319},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2001-311","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.8.5536","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.5536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nue.org/people/okuno/EuroSpeech01-nakadai.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W36769352","https://openalex.org/W70999531","https://openalex.org/W160900442","https://openalex.org/W1494888225","https://openalex.org/W1567997379","https://openalex.org/W2028310195","https://openalex.org/W2096082251","https://openalex.org/W2121065047"],"related_works":["https://openalex.org/W2084086966","https://openalex.org/W2023861399","https://openalex.org/W2730915376","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2626306547","https://openalex.org/W2320915480","https://openalex.org/W2021396365","https://openalex.org/W2362990116"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"real-time":[3,35,105],"multiple":[4],"speaker":[5,51],"tracking":[6],"is":[7,11],"addressed,":[8],"because":[9],"it":[10],"essential":[12],"in":[13,23,81,83],"robot":[14],"perception":[15],"and":[16,34,57,74,91],"humanrobot":[17],"social":[18],"interaction.":[19],"The":[20],"difficulty":[21],"lies":[22],"treating":[24],"a":[25,108],"mixture":[26],"of":[27,40,46,49,64,71,85],"sounds,":[28],"occlusion":[29],"(some":[30],"talkers":[31],"are":[32],"hidden)":[33],"processing.":[36,106],"Our":[37],"approach":[38],"consists":[39],"three":[41,97],"components;":[42],"(1)":[43],"the":[44,47,62,93],"extraction":[45],"direction":[48,67],"each":[50,65],"by":[52,68,100],"using":[53],"interaural":[54,58],"phase":[55],"difference":[56],"intensity":[59],"difference,":[60],"(2)":[61],"resolution":[63],"speaker&amp;apos;s":[66],"multi-modal":[69],"integration":[70],"audition,":[72],"vision":[73],"motion":[75,82],"with":[76],"canceling":[77],"inevitable":[78],"motor":[79],"noises":[80],"case":[84],"an":[86],"unseen":[87],"or":[88],"silent":[89],"speaker,":[90],"(3)":[92],"distributed":[94],"implementation":[95],"to":[96,103],"PCs":[98],"connected":[99],"TCP/IP":[101],"network":[102],"attain":[104],"As":[107],"result,":[109],"we...":[110]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
