{"id":"https://openalex.org/W106296304","doi":"https://doi.org/10.21437/eurospeech.2003-631","title":"Detection and separation of speech segment using audio and video information fusion","display_name":"Detection and separation of speech segment using audio and video information fusion","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W106296304","doi":"https://doi.org/10.21437/eurospeech.2003-631","mag":"106296304"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5112430812","display_name":"Futoshi Asano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Futoshi Asano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108625998","display_name":"Yoichi Motomura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoichi Motomura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073671259","display_name":"Hideki Asoh","orcid":"https://orcid.org/0000-0002-0891-3782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hideki Asoh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034557056","display_name":"Takashi Yoshimura","orcid":"https://orcid.org/0000-0002-0760-1867"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Yoshimura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111782038","display_name":"Naoyuki Ichimura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoyuki Ichimura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016899140","display_name":"Kiyoshi Yamamoto","orcid":"https://orcid.org/0000-0001-9351-5174"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiyoshi Yamamoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043034668","display_name":"Nobuhiko Kitawaki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuhiko Kitawaki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1865,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77922323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2257","last_page":"2260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8241000175476074,"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":0.8241000175476074,"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":0.7083885073661804},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6175779700279236},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6148625016212463},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6127899289131165},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5067799687385559},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4179392457008362},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.40328913927078247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39958328008651733},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37290698289871216},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32367879152297974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.06689059734344482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7083885073661804},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6175779700279236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6148625016212463},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6127899289131165},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5067799687385559},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4179392457008362},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.40328913927078247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39958328008651733},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37290698289871216},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32367879152297974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06689059734344482},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2121486117","https://openalex.org/W1995163783","https://openalex.org/W2042419400","https://openalex.org/W2368779261","https://openalex.org/W3015225820","https://openalex.org/W2403025337","https://openalex.org/W3163107903","https://openalex.org/W2000099289","https://openalex.org/W2991037759"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}