{"id":"https://openalex.org/W2790234110","doi":"https://doi.org/10.1145/3180308.3180323","title":"Detecting Utterance Scenes of a Specific Person","display_name":"Detecting Utterance Scenes of a Specific Person","publication_year":2018,"publication_date":"2018-03-05","ids":{"openalex":"https://openalex.org/W2790234110","doi":"https://doi.org/10.1145/3180308.3180323","mag":"2790234110"},"language":"en","primary_location":{"id":"doi:10.1145/3180308.3180323","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3180308.3180323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 23rd International Conference on Intelligent User Interfaces","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/A5109545869","display_name":"Kunihiko Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kunihiko Sato","raw_affiliation_strings":["The University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082649952","display_name":"Jun Rekimoto","orcid":"https://orcid.org/0000-0002-3629-2514"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Rekimoto","raw_affiliation_strings":["The University of Tokyo / Sony CSL, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo / Sony CSL, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I4210122684","https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109545869"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02075274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9498000144958496,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9498000144958496,"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/utterance","display_name":"Utterance","score":0.8053281307220459},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6942534446716309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5380622148513794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39498579502105713},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39391404390335083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3269510269165039}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8053281307220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6942534446716309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5380622148513794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39498579502105713},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39391404390335083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3269510269165039}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3180308.3180323","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3180308.3180323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 23rd International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2074511636","https://openalex.org/W2161605020","https://openalex.org/W2654729393"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,84],"propose":[1],"a":[2,9,22,46,55,62,68,76],"system":[3,30],"that":[4],"detects":[5],"the":[6,15,19,26,36,80,87,92,95,99,103],"scene,":[7],"where":[8,54],"specific":[10,56,63,77],"speaker":[11,57,78],"is":[12,58],"speaking":[13],"in":[14,25,45],"video,":[16],"and":[17,98],"displays":[18],"site":[20],"as":[21],"heat":[23],"map":[24],"video's":[27],"timeline.":[28],"This":[29],"enables":[31],"users":[32],"to":[33,35,40,73],"skip":[34],"timeline":[37],"they":[38],"want":[39],"hear":[41],"by":[42],"detecting":[43],"scenes":[44],"drama,":[47],"talk":[48],"show,":[49],"or":[50],"discussion":[51],"TV":[52],"program,":[53],"speaking.":[59],"To":[60],"detect":[61],"speaker's":[64],"utterance,":[65],"we":[66],"develop":[67],"deep":[69],"neural":[70],"network":[71],"(DNN)":[72],"extract":[74],"only":[75],"from":[79],"original":[81],"sound":[82],"source.":[83],"also":[85],"implement":[86],"detection":[88,104],"algorithm":[89],"based":[90],"on":[91],"output":[93],"of":[94],"proposed":[96],"DNN":[97],"interface":[100],"for":[101],"displaying":[102],"result.":[105]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
