{"id":"https://openalex.org/W2066998189","doi":"https://doi.org/10.1117/12.587870","title":"&lt;title&gt;Multimodal approach for speaker identification in news programs&lt;/title&gt;","display_name":"&lt;title&gt;Multimodal approach for speaker identification in news programs&lt;/title&gt;","publication_year":2005,"publication_date":"2005-01-17","ids":{"openalex":"https://openalex.org/W2066998189","doi":"https://doi.org/10.1117/12.587870","mag":"2066998189"},"language":"en","primary_location":{"id":"doi:10.1117/12.587870","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.587870","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","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/A5045799487","display_name":"Anthony F. Martone","orcid":"https://orcid.org/0000-0001-9596-5400"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anthony F. Martone","raw_affiliation_strings":["Purdue Univ. (United States)","Purdue University , USA"],"affiliations":[{"raw_affiliation_string":"Purdue Univ. (United States)","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043578524","display_name":"Cuneyt M. Taskiran","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cuneyt M. Taskiran","raw_affiliation_strings":["Purdue Univ. (United States)","Purdue University , USA"],"affiliations":[{"raw_affiliation_string":"Purdue Univ. (United States)","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University , USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089688702","display_name":"Edward J. Delp","orcid":"https://orcid.org/0000-0002-2909-7323"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward J. Delp","raw_affiliation_strings":["Purdue Univ. (United States)","Purdue University , USA"],"affiliations":[{"raw_affiliation_string":"Purdue Univ. (United States)","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Purdue University , USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045799487"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.5875,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69734345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5682","issue":null,"first_page":"308","last_page":"316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922000169754028,"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":0.8033720850944519},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.686118483543396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6684403419494629},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5913702249526978},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5689758062362671},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49034929275512695},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.45229092240333557},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44048595428466797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36386430263519287},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.08472704887390137},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.066750168800354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8033720850944519},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.686118483543396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6684403419494629},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5913702249526978},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5689758062362671},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49034929275512695},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.45229092240333557},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44048595428466797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36386430263519287},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.08472704887390137},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.066750168800354},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.587870","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.587870","pdf_url":null,"source":{"id":"https://openalex.org/S183492911","display_name":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","issn_l":"0277-786X","issn":["0277-786X","1996-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315543","host_organization_name":"SPIE","host_organization_lineage":["https://openalex.org/P4310315543"],"host_organization_lineage_names":["SPIE"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPIE Proceedings","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":5,"referenced_works":["https://openalex.org/W1969228515","https://openalex.org/W1985070822","https://openalex.org/W2075662881","https://openalex.org/W2085797365","https://openalex.org/W2161572620"],"related_works":["https://openalex.org/W2410566519","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W4234190324","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1585155462","https://openalex.org/W2249138175","https://openalex.org/W2154141294"],"abstract_inverted_index":{"The":[0],"process":[1],"of":[2,32,34,39,50,63,77],"identifying":[3],"speakers":[4],"in":[5,52],"a":[6,17,35,48],"news":[7],"program":[8],"is":[9,57,85],"difficult":[10],"using":[11],"only":[12],"text":[13,23,65],"information.":[14,68],"We":[15],"propose":[16],"system":[18],"that":[19,74],"will":[20,70],"first":[21],"perform":[22],"and":[24,44,66],"video":[25,67],"processing":[26],"separately":[27],"to":[28,46,59],"identify":[29,47,60],"the":[30,53,61,64,75],"start":[31,38],"speech":[33,40],"speaker.":[36],"These":[37],"locations":[41,79],"are":[42],"aligned":[43],"used":[45],"change":[49,76],"speaker":[51,78],"program.":[54],"An":[55],"analysis":[56],"performed":[58],"contribution":[62],"It":[69],"be":[71,72],"shown":[73],"identified":[80],"by":[81],"our":[82],"alignment":[83],"algorithm":[84],"more":[86],"accurate":[87],"then":[88],"either":[89],"mode":[90],"individually.":[91]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
