{"id":"https://openalex.org/W2130102735","doi":"https://doi.org/10.1145/1180995.1181037","title":"EM detection of common origin of multi-modal cues","display_name":"EM detection of common origin of multi-modal cues","publication_year":2006,"publication_date":"2006-11-02","ids":{"openalex":"https://openalex.org/W2130102735","doi":"https://doi.org/10.1145/1180995.1181037","mag":"2130102735"},"language":"en","primary_location":{"id":"doi:10.1145/1180995.1181037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1180995.1181037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th international conference on Multimodal 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/A5053745317","display_name":"A. Noulas","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"A. K. Noulas","raw_affiliation_strings":["University Of Amsterdam and Intelligent Systems Lab Amsterdam","University Of Amsterdam and Intelligent Systems Lab Amsterdam#TAB#"],"affiliations":[{"raw_affiliation_string":"University Of Amsterdam and Intelligent Systems Lab Amsterdam","institution_ids":[]},{"raw_affiliation_string":"University Of Amsterdam and Intelligent Systems Lab Amsterdam#TAB#","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049349937","display_name":"Ben Kr\u00f6se","orcid":"https://orcid.org/0000-0003-1237-0618"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"B. J. A. Kr\u00f6se","raw_affiliation_strings":["University Of Amsterdam and Intelligent Systems Lab Amsterdam","University Of Amsterdam and Intelligent Systems Lab Amsterdam#TAB#"],"affiliations":[{"raw_affiliation_string":"University Of Amsterdam and Intelligent Systems Lab Amsterdam","institution_ids":[]},{"raw_affiliation_string":"University Of Amsterdam and Intelligent Systems Lab Amsterdam#TAB#","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053745317"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.9672,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.75600524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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/T10860","display_name":"Speech and Audio Processing","score":0.9896000027656555,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9861999750137329,"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":0.7475247383117676},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.736760675907135},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5653931498527527},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.561799943447113},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.5554184913635254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5453563928604126},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5433867573738098},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.514178991317749},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5024209022521973},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45577123761177063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4238182604312897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38328054547309875},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34682726860046387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475247383117676},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.736760675907135},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5653931498527527},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.561799943447113},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.5554184913635254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5453563928604126},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5433867573738098},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.514178991317749},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5024209022521973},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45577123761177063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4238182604312897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38328054547309875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34682726860046387},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1180995.1181037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1180995.1181037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th international conference on Multimodal interfaces","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire_cris_publications/b30a6209-ec9b-46e0-9a5f-34dfffb768ea","is_oa":false,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/em-detection-of-common-origin-of-multimodal-cues(b30a6209-ec9b-46e0-9a5f-34dfffb768ea).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Noulas, A & Kr\u00f6se, B J A 2006, E.M. detection of Common Origin of Multi-Modal Cues. in Proceedings of the 8th international conference on Multimodal interfaces. Banff, Alberta, Canada, pp. 201-208, International Conference on Multimodal Interfaces, 1/01/06.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:dare.uva.nl:publications/b30a6209-ec9b-46e0-9a5f-34dfffb768ea","is_oa":false,"landing_page_url":"http://dare.uva.nl/personal/pure/en/publications/em-detection-of-common-origin-of-multimodal-cues(b30a6209-ec9b-46e0-9a5f-34dfffb768ea).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Noulas, A & Kr\u00f6se, B J A 2006, E.M. detection of Common Origin of Multi-Modal Cues. in Proceedings of the 8th international conference on Multimodal interfaces. Banff, Alberta, Canada, pp. 201-208, International Conference on Multimodal Interfaces, 1/01/06.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:uvapub:oai:dare.uva.nl:publications/b30a6209-ec9b-46e0-9a5f-34dfffb768ea","is_oa":false,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/em-detection-of-common-origin-of-multimodal-cues(b30a6209-ec9b-46e0-9a5f-34dfffb768ea).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 8th international conference on Multimodal interfaces, 201 - 208","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W1486632395","https://openalex.org/W1499712254","https://openalex.org/W1567497459","https://openalex.org/W1645165343","https://openalex.org/W1797158261","https://openalex.org/W1973436000","https://openalex.org/W1986647142","https://openalex.org/W1989702938","https://openalex.org/W1996758056","https://openalex.org/W2075662881","https://openalex.org/W2098693229","https://openalex.org/W2106488367","https://openalex.org/W2121601095","https://openalex.org/W2125838338","https://openalex.org/W2126326837","https://openalex.org/W2163973301","https://openalex.org/W3097096317","https://openalex.org/W3215887389"],"related_works":["https://openalex.org/W2541791370","https://openalex.org/W2952745240","https://openalex.org/W2035976912","https://openalex.org/W2949074159","https://openalex.org/W4301143707","https://openalex.org/W4298715519","https://openalex.org/W3094187672","https://openalex.org/W3198037411","https://openalex.org/W2474574787","https://openalex.org/W2546942002"],"abstract_inverted_index":{"Content":[0],"analysis":[1],"of":[2,29,37,44,83,98],"clips":[3],"containing":[4],"people":[5],"speaking":[6],"involves":[7],"processing":[8],"informative":[9],"cues":[10,16,46],"coming":[11],"from":[12,22],"different":[13],"modalities.":[14],"These":[15],"are":[17,116],"usually":[18],"the":[19,23,27,30,34,38,48,61,73,78,81,84,90,96,99,102,106,109],"words":[20],"extracted":[21,62],"audio":[24],"modality,":[25],"and":[26,67,101],"identity":[28,97],"persons":[31],"appearing":[32],"in":[33,76],"video":[35],"modality":[36],"clip.":[39],"To":[40],"achieve":[41],"efficient":[42],"assignment":[43],"these":[45],"to":[47,89],"person":[49,110],"that":[50,59,94,112],"created":[51],"them,":[52],"we":[53],"propose":[54],"a":[55],"Bayesian":[56],"network":[57],"model":[58],"utilizes":[60],"feature":[63],"characteristics,":[64],"their":[65,68],"relations":[66],"temporal":[69],"patterns.":[70],"We":[71],"use":[72],"EM":[74],"algorithm":[75],"which":[77],"E-step":[79],"estimates":[80],"expectation":[82,115],"complete-data":[85],"log-likelihood":[86],"with":[87,128],"respect":[88],"hidden":[91],"variables":[92],"-":[93],"is":[95],"speakers":[100],"visible":[103],"persons.":[104],"In":[105],"M-step":[107],",":[108],"models":[111],"maximize":[113],"this":[114],"computed.":[117],"This":[118],"framework":[119],"produces":[120],"excellent":[121],"results,":[122],"exhibiting":[123],"exceptional":[124],"robustness":[125],"when":[126],"dealing":[127],"low":[129],"quality":[130],"data.":[131]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"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"}
