{"id":"https://openalex.org/W2049687350","doi":"https://doi.org/10.1145/1877972.1877996","title":"Combining dynamic texture and structural features for speaker identification","display_name":"Combining dynamic texture and structural features for speaker identification","publication_year":2010,"publication_date":"2010-10-29","ids":{"openalex":"https://openalex.org/W2049687350","doi":"https://doi.org/10.1145/1877972.1877996","mag":"2049687350"},"language":"en","primary_location":{"id":"doi:10.1145/1877972.1877996","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1877972.1877996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM workshop on Multimedia in forensics, security and intelligence","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/A5082301986","display_name":"Guoying Zhao","orcid":"https://orcid.org/0000-0003-3694-206X"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Guoying Zhao","raw_affiliation_strings":["University of Oulu, Finland, Oulu, Finland","University of Oulu: Finland, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Finland, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]},{"raw_affiliation_string":"University of Oulu: Finland, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083815471","display_name":"Xiaohua Huang","orcid":"https://orcid.org/0000-0001-8897-3517"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiaohua Huang","raw_affiliation_strings":["University of Oulu, Finland, Oulu, Finland","University of Oulu: Finland, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Finland, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]},{"raw_affiliation_string":"University of Oulu: Finland, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061942571","display_name":"Yulia Gizatdinova","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yulia Gizatdinova","raw_affiliation_strings":["Tampere University, Finland, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Finland, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014611768","display_name":"Matti Pietik\u00e4inen","orcid":"https://orcid.org/0000-0003-2263-6731"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Matti Pietik\u00e4inen","raw_affiliation_strings":["University of Oulu, Finland, Oulu, Finland","University of Oulu: Finland, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Finland, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]},{"raw_affiliation_string":"University of Oulu: Finland, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082301986"],"corresponding_institution_ids":["https://openalex.org/I98381234"],"apc_list":null,"apc_paid":null,"fwci":3.67757042,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93528915,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"98"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9973000288009644,"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":0.7734432220458984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7538492679595947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6384785175323486},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5318716764450073},{"id":"https://openalex.org/keywords/local-binary-patterns","display_name":"Local binary patterns","score":0.5304063558578491},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5296905636787415},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.5208266973495483},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.46230757236480713},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44999587535858154},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41567832231521606},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36816519498825073},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3222997486591339},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.1487663984298706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734432220458984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7538492679595947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6384785175323486},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5318716764450073},{"id":"https://openalex.org/C87335442","wikidata":"https://www.wikidata.org/wiki/Q2494345","display_name":"Local binary patterns","level":4,"score":0.5304063558578491},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5296905636787415},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.5208266973495483},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.46230757236480713},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44999587535858154},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41567832231521606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36816519498825073},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3222997486591339},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.1487663984298706},{"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:10.1145/1877972.1877996","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1877972.1877996","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM workshop on Multimedia in forensics, security and intelligence","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":24,"referenced_works":["https://openalex.org/W192922316","https://openalex.org/W1527240141","https://openalex.org/W1536323972","https://openalex.org/W1539148904","https://openalex.org/W1655137980","https://openalex.org/W1664547674","https://openalex.org/W1974783905","https://openalex.org/W1993087016","https://openalex.org/W2002576197","https://openalex.org/W2014408663","https://openalex.org/W2075306129","https://openalex.org/W2097627987","https://openalex.org/W2104724950","https://openalex.org/W2106284211","https://openalex.org/W2106930486","https://openalex.org/W2126909398","https://openalex.org/W2129318657","https://openalex.org/W2136155248","https://openalex.org/W2139916508","https://openalex.org/W2140291188","https://openalex.org/W2144012665","https://openalex.org/W2157085398","https://openalex.org/W2163352848","https://openalex.org/W2164598857"],"related_works":["https://openalex.org/W2055219403","https://openalex.org/W2791313072","https://openalex.org/W3166997759","https://openalex.org/W2794489335","https://openalex.org/W2080437822","https://openalex.org/W2153027217","https://openalex.org/W2855870609","https://openalex.org/W1589677080","https://openalex.org/W2770255720","https://openalex.org/W1509533962"],"abstract_inverted_index":{"Visual":[0],"information":[1,58],"from":[2,49,76],"captured":[3],"video":[4],"is":[5],"important":[6],"for":[7,55,80,103],"speaker":[8],"identification":[9],"under":[10],"noisy":[11],"conditions":[12],"that":[13],"have":[14],"background":[15],"noise":[16],"or":[17],"cross":[18],"talk":[19],"among":[20],"speakers.":[21],"In":[22,108],"this":[23],"paper,":[24],"we":[25],"propose":[26],"local":[27,45],"spatiotemporal":[28,104],"descriptors":[29],"to":[30,124],"represent":[31],"and":[32,66,88,94,113],"recognize":[33],"speakers":[34],"based":[35],"solely":[36],"on":[37,111],"visual":[38],"features.":[39,127],"Spatiotemporal":[40],"dynamic":[41,86],"texture":[42,87],"features":[43,73,90],"of":[44,85],"binary":[46],"patterns":[47],"extracted":[48,75],"localized":[50],"mouth":[51],"regions":[52],"are":[53,74],"used":[54],"describing":[56],"motion":[57,93],"in":[59,106],"utterances,":[60],"which":[61],"can":[62],"capture":[63],"the":[64,77,100,116,125],"spatial":[65],"temporal":[67],"transition":[68],"characteristics.":[69,83],"Structural":[70],"edge":[71],"map":[72],"image":[78],"frames":[79],"representing":[81],"appearance":[82,95],"Combination":[84],"structural":[89],"takes":[91],"both":[92],"together":[96],"into":[97],"account,":[98],"providing":[99],"description":[101],"ability":[102],"development":[105],"speech.":[107],"our":[109],"experiments":[110],"BANCA":[112],"XM2VTS":[114],"databases":[115],"proposed":[117],"method":[118],"obtained":[119],"promising":[120],"recognition":[121],"results":[122],"comparing":[123],"other":[126]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}