{"id":"https://openalex.org/W2125046265","doi":"https://doi.org/10.1109/icpr.2006.967","title":"Real-time Sound Source Localization Based on Audiovisual Frequency Integration","display_name":"Real-time Sound Source Localization Based on Audiovisual Frequency Integration","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2125046265","doi":"https://doi.org/10.1109/icpr.2006.967","mag":"2125046265"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2006.967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2006.967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Conference on Pattern Recognition (ICPR'06)","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/A5101453043","display_name":"Toshio Tsuji","orcid":"https://orcid.org/0000-0002-7689-3963"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Tsuji","raw_affiliation_strings":["Department of Aritificial Complex Systems, Hiroshima University, Higashihiroshima, Japan","Hiroshima University (Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aritificial Complex Systems, Hiroshima University, Higashihiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]},{"raw_affiliation_string":"Hiroshima University (Japan)","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110502000","display_name":"Kenkichi Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Yamamoto","raw_affiliation_strings":["Department of Aritificial Complex Systems, Hiroshima University, Higashihiroshima, Japan","Hiroshima University (Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aritificial Complex Systems, Hiroshima University, Higashihiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]},{"raw_affiliation_string":"Hiroshima University (Japan)","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060719224","display_name":"Idaku Ishii","orcid":"https://orcid.org/0000-0002-7728-2363"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"I. Ishii","raw_affiliation_strings":["Department of Aritificial Complex Systems, Hiroshima University, Higashihiroshima, Japan","Hiroshima University (Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aritificial Complex Systems, Hiroshima University, Higashihiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]},{"raw_affiliation_string":"Hiroshima University (Japan)","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":null,"apc_paid":null,"fwci":0.6466,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69084025,"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":"322","last_page":"325"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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":0.9945999979972839,"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/acoustic-source-localization","display_name":"Acoustic source localization","score":0.7676099538803101},{"id":"https://openalex.org/keywords/brightness","display_name":"Brightness","score":0.6461623907089233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6195040941238403},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5635161399841309},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5350884795188904},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.524827778339386},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5146139860153198},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.49657517671585083},{"id":"https://openalex.org/keywords/vibration","display_name":"Vibration","score":0.47459882497787476},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4324013590812683},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.424649178981781},{"id":"https://openalex.org/keywords/time-delay-and-integration","display_name":"Time delay and integration","score":0.4196772277355194},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3712225556373596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32655179500579834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2863987982273102},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.17738297581672668}],"concepts":[{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.7676099538803101},{"id":"https://openalex.org/C125245961","wikidata":"https://www.wikidata.org/wiki/Q221656","display_name":"Brightness","level":2,"score":0.6461623907089233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6195040941238403},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5635161399841309},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5350884795188904},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.524827778339386},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5146139860153198},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.49657517671585083},{"id":"https://openalex.org/C198394728","wikidata":"https://www.wikidata.org/wiki/Q3695508","display_name":"Vibration","level":2,"score":0.47459882497787476},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4324013590812683},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.424649178981781},{"id":"https://openalex.org/C96566525","wikidata":"https://www.wikidata.org/wiki/Q7805282","display_name":"Time delay and integration","level":2,"score":0.4196772277355194},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3712225556373596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32655179500579834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2863987982273102},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17738297581672668},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2006.967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2006.967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Conference on Pattern Recognition (ICPR'06)","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":4,"referenced_works":["https://openalex.org/W2055899945","https://openalex.org/W2130432819","https://openalex.org/W2146053319","https://openalex.org/W4247773827"],"related_works":["https://openalex.org/W3011070339","https://openalex.org/W2108013559","https://openalex.org/W2288611238","https://openalex.org/W1485388545","https://openalex.org/W2289868279","https://openalex.org/W2349923422","https://openalex.org/W2998173332","https://openalex.org/W2159006459","https://openalex.org/W2143986816","https://openalex.org/W2766036819"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"pixelwise":[3,63],"sound":[4,24,64],"source":[5,65],"localization":[6,14,66],"algorithm":[7],"based":[8],"on":[9],"audiovisual":[10],"frequency":[11],"integration.":[12],"The":[13],"is":[15],"realized":[16],"by":[17],"detecting":[18],"the":[19,27,30,37,45,51,62],"common":[20,38],"vibration":[21,39],"dynamics":[22],"of":[23],"sources":[25],"in":[26,50],"audio":[28],"and":[29,61],"brightness":[31],"signal.":[32],"In":[33],"order":[34],"to":[35],"detect":[36],"dynamics,":[40],"temporal":[41],"correlation":[42],"values":[43],"between":[44],"two":[46],"signals":[47],"are":[48,56,68],"calculated":[49],"algorithm.":[52],"Several":[53],"experimental":[54],"results":[55],"shown":[57],"for":[58],"vibrated":[59],"objects,":[60],"images":[67],"obtained":[69]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
