{"id":"https://openalex.org/W2071795835","doi":"https://doi.org/10.1155/s1110865704402303","title":"Detection and Separation of Speech Event Using Audio and Video Information Fusion and Its Application to Robust Speech Interface","display_name":"Detection and Separation of Speech Event Using Audio and Video Information Fusion and Its Application to Robust Speech Interface","publication_year":2004,"publication_date":"2004-09-18","ids":{"openalex":"https://openalex.org/W2071795835","doi":"https://doi.org/10.1155/s1110865704402303","mag":"2071795835"},"language":"en","primary_location":{"id":"doi:10.1155/s1110865704402303","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865704402303","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865704402303","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865704402303","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112430812","display_name":"Futoshi Asano","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Futoshi Asano","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016899140","display_name":"Kiyoshi Yamamoto","orcid":"https://orcid.org/0000-0001-9351-5174"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]},{"id":"https://openalex.org/I24254649","display_name":"Tsukuba University of Technology","ror":"https://ror.org/057bx9y85","country_code":"JP","type":"education","lineage":["https://openalex.org/I24254649"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kiyoshi Yamamoto","raw_affiliation_strings":["Department of Computer Science, Tsukuba University, Tsukuba, 305-8573, Japan","Department of Computer Science, Tsukuba University, Tsukuba, Japan#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tsukuba University, Tsukuba, 305-8573, Japan","institution_ids":["https://openalex.org/I146399215","https://openalex.org/I24254649"]},{"raw_affiliation_string":"Department of Computer Science, Tsukuba University, Tsukuba, Japan#TAB#","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060386554","display_name":"Isao Hara","orcid":"https://orcid.org/0000-0003-4542-4045"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Isao Hara","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006504365","display_name":"Jun Ogata","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Ogata","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034557056","display_name":"Takashi Yoshimura","orcid":"https://orcid.org/0000-0002-0760-1867"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Yoshimura","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108625998","display_name":"Yoichi Motomura","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Motomura","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111782038","display_name":"Naoyuki Ichimura","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoyuki Ichimura","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073671259","display_name":"Hideki Asoh","orcid":"https://orcid.org/0000-0002-0891-3782"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Asoh","raw_affiliation_strings":["Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Tsukuba, 305-8568, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Information Technology Research Institute National Institute of Advanced Industrial Science and Technology,Tsukuba,Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1140,"currency":"GBP","value_usd":1398},"apc_paid":{"value":1140,"currency":"GBP","value_usd":1398},"fwci":2.2939,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.88348499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2004","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9962999820709229,"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/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"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":0.8080509305000305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7416091561317444},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.670939564704895},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6281826496124268},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5776922106742859},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5399228930473328},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5357593297958374},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5105081796646118},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.4414841830730438},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4270760715007782},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4190342128276825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35726550221443176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080509305000305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7416091561317444},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.670939564704895},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6281826496124268},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5776922106742859},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5399228930473328},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5357593297958374},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5105081796646118},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.4414841830730438},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4270760715007782},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4190342128276825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35726550221443176},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1155/s1110865704402303","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865704402303","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865704402303","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1155/s1110865704402303","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865704402303","pdf_url":"https://asp-eurasipjournals.springeropen.com/counter/pdf/10.1155/S1110865704402303","source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2071795835.pdf","grobid_xml":"https://content.openalex.org/works/W2071795835.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W106296304","https://openalex.org/W138260957","https://openalex.org/W1506558619","https://openalex.org/W1578414812","https://openalex.org/W1673131496","https://openalex.org/W1755360231","https://openalex.org/W2078813998","https://openalex.org/W2096710051","https://openalex.org/W2100969003","https://openalex.org/W2109914127","https://openalex.org/W2113638573","https://openalex.org/W2117061651","https://openalex.org/W2129735148","https://openalex.org/W2146871184","https://openalex.org/W2147347395","https://openalex.org/W2164427415","https://openalex.org/W2166766408","https://openalex.org/W2170160744","https://openalex.org/W2295986502","https://openalex.org/W2578808052","https://openalex.org/W4299670631","https://openalex.org/W6624852173","https://openalex.org/W6676365419","https://openalex.org/W6684327735"],"related_works":["https://openalex.org/W2184127972","https://openalex.org/W2964829415","https://openalex.org/W3159882232","https://openalex.org/W642007152","https://openalex.org/W4210930959","https://openalex.org/W2071795835","https://openalex.org/W2343205865","https://openalex.org/W2550171623","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"A":[0,74],"method":[1],"of":[2,43,53,84,98,108],"detecting":[3,18],"speech":[4,19,54,64,72,86,91,110,116,123,128],"events":[5,55,65,117],"in":[6,69],"a":[7,24,36,82],"multiple-sound-source":[8],"condition":[9],"using":[10,23],"audio":[11],"and":[12,27,51],"video":[13],"information":[14,47,60,107,113],"is":[15,33,66,79,118],"proposed.":[16],"For":[17],"events,":[20],"sound":[21],"localization":[22],"microphone":[25],"array":[26],"human":[28],"tracking":[29],"by":[30,35,121],"stereo":[31],"vision":[32],"combined":[34],"Bayesian":[37,45],"network.":[38],"From":[39],"the":[40,44,49,62,70,85,90,99,106,109,115,122,127],"inference":[41],"results":[42],"network,":[46],"on":[48,61,105,114],"time":[50],"location":[52],"can":[56],"be":[57],"known.":[58],"The":[59,96,112],"detected":[63],"then":[67],"utilized":[68],"robust":[71],"interface.":[73],"maximum":[75],"likelihood":[76],"adaptive":[77],"beamformer":[78,100],"employed":[80],"as":[81],"preprocessor":[83],"recognizer":[87,124],"to":[88],"separate":[89],"signal":[92],"from":[93],"environmental":[94],"noise.":[95],"coefficients":[97],"are":[101],"kept":[102],"updated":[103],"based":[104],"events.":[111],"also":[119],"used":[120],"for":[125],"extracting":[126],"segment.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
