{"id":"https://openalex.org/W2408371159","doi":"https://doi.org/10.21437/interspeech.2011-237","title":"Robust bimodal person identification using face and speech with limited training data and corruption of both modalities","display_name":"Robust bimodal person identification using face and speech with limited training data and corruption of both modalities","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2408371159","doi":"https://doi.org/10.21437/interspeech.2011-237","mag":"2408371159"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-237","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pureadmin.qub.ac.uk/ws/files/16286083/McLaughlin_Interspeech_2011.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049691746","display_name":"Niall McLaughlin","orcid":"https://orcid.org/0000-0002-0917-9145"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Niall McLaughlin","raw_affiliation_strings":["Institute of ECIT, Queen's University Belfast, Belfast, BT3 9DT, UK"],"affiliations":[{"raw_affiliation_string":"Institute of ECIT, Queen's University Belfast, Belfast, BT3 9DT, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838286","display_name":"Ji Ming","orcid":"https://orcid.org/0000-0001-6887-2591"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ji Ming","raw_affiliation_strings":["Institute of ECIT, Queen's University Belfast, Belfast, BT3 9DT, UK"],"affiliations":[{"raw_affiliation_string":"Institute of ECIT, Queen's University Belfast, Belfast, BT3 9DT, UK","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000739686","display_name":"Danny Crookes","orcid":"https://orcid.org/0000-0002-3533-6095"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Danny Crookes","raw_affiliation_strings":["Institute of ECIT, Queen's University Belfast, Belfast, BT3 9DT, UK"],"affiliations":[{"raw_affiliation_string":"Institute of ECIT, Queen's University Belfast, Belfast, BT3 9DT, UK","institution_ids":["https://openalex.org/I126231945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049691746"],"corresponding_institution_ids":["https://openalex.org/I126231945"],"apc_list":null,"apc_paid":null,"fwci":0.7841,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78219822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"585","last_page":"588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9972000122070312,"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/T11448","display_name":"Face recognition and analysis","score":0.9972000122070312,"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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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/T10057","display_name":"Face and Expression Recognition","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.76910799741745},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6513881683349609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6032313108444214},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6011306047439575},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5789538621902466},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.5477662086486816},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5296542048454285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5118805170059204},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4861619174480438},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.4695741832256317},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4686433970928192},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4575132727622986},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44800692796707153},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.42197906970977783},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4142093360424042},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.41027557849884033},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1966281533241272}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76910799741745},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6513881683349609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6032313108444214},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6011306047439575},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5789538621902466},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.5477662086486816},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5296542048454285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5118805170059204},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4861619174480438},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4695741832256317},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4686433970928192},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4575132727622986},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44800692796707153},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.42197906970977783},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4142093360424042},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.41027557849884033},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1966281533241272},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-237","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:openaire/4fada32a-8d59-4eaf-b5a1-b44a1eaa35ba","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/4fada32a-8d59-4eaf-b5a1-b44a1eaa35ba","pdf_url":"https://pureadmin.qub.ac.uk/ws/files/16286083/McLaughlin_Interspeech_2011.pdf","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"McLaughlin, N, Ji, M & Crookes, D 2011, Robust bimodal person identification using face and speech with limited training data and corruption of both modalities. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 585-588.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.qub.ac.uk/portal:openaire/4fada32a-8d59-4eaf-b5a1-b44a1eaa35ba","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/4fada32a-8d59-4eaf-b5a1-b44a1eaa35ba","pdf_url":"https://pureadmin.qub.ac.uk/ws/files/16286083/McLaughlin_Interspeech_2011.pdf","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"McLaughlin, N, Ji, M & Crookes, D 2011, Robust bimodal person identification using face and speech with limited training data and corruption of both modalities. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 585-588.","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2408371159.pdf","grobid_xml":"https://content.openalex.org/works/W2408371159.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1575210522","https://openalex.org/W2005262108","https://openalex.org/W2014447400","https://openalex.org/W2033428711","https://openalex.org/W2101231430","https://openalex.org/W2102863932","https://openalex.org/W2103056131","https://openalex.org/W2103208299","https://openalex.org/W2129122669"],"related_works":["https://openalex.org/W1916685473","https://openalex.org/W2055682261","https://openalex.org/W1993363272","https://openalex.org/W2186390138","https://openalex.org/W2060035984","https://openalex.org/W2790129917","https://openalex.org/W2992856432","https://openalex.org/W2100638064","https://openalex.org/W1552490587","https://openalex.org/W3035701170"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,25,38,48,54,66,123],"novel":[4],"method":[5,148],"of":[6,27,41,138],"audio-visual":[7],"fusion":[8],"for":[9,44,59,72],"person":[10],"identification":[11],"where":[12],"both":[13],"the":[14,31,102,110,129,143],"speech":[15,51,139],"and":[16,22,53,65,74,89,95,106,131,140],"facial":[17,57],"modalities":[18],"may":[19],"be":[20],"corrupted,":[21],"there":[23,36],"is":[24,37],"lack":[26],"prior":[28],"knowledge":[29],"about":[30],"corruption.":[32,116],"Furthermore,":[33],"we":[34],"assume":[35],"limited":[39,79],"amount":[40],"training":[42,50,56,80,97,105],"data":[43,81,87,125],"each":[45,60],"modality":[46],"(e.g.,":[47],"short":[49],"segment":[52],"single":[55],"image":[58],"person).":[61],"A":[62],"new":[63,147],"representation":[64],"modified":[67],"cosine":[68],"similarity":[69],"are":[70,98],"introduced":[71],"combining":[73],"comparing":[75],"bimodal":[76,115,124],"features":[77],"with":[78,134],"as":[82,84],"well":[83],"vastly":[85],"differing":[86],"rates":[88],"feature":[90,93],"sizes.":[91],"Optimal":[92],"selection":[94],"multicondition":[96],"used":[99],"to":[100,113],"reduce":[101],"mismatch":[103],"between":[104],"testing,":[107],"thereby":[108],"making":[109],"system":[111],"robust":[112],"unknown":[114],"Experiments":[117],"have":[118],"been":[119],"carried":[120],"out":[121],"on":[122],"set":[126],"created":[127],"from":[128],"SPIDRE":[130],"AR":[132],"databases":[133],"variable":[135],"noise":[136],"corruption":[137],"occlusion":[141],"in":[142],"face":[144],"images.":[145],"The":[146],"has":[149],"demonstrated":[150],"improved":[151],"recognition":[152],"accuracy.":[153]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}