{"id":"https://openalex.org/W2287407690","doi":"https://doi.org/10.1145/2818346.2820780","title":"Who's Speaking?","display_name":"Who's Speaking?","publication_year":2015,"publication_date":"2015-11-06","ids":{"openalex":"https://openalex.org/W2287407690","doi":"https://doi.org/10.1145/2818346.2820780","mag":"2287407690"},"language":"en","primary_location":{"id":"doi:10.1145/2818346.2820780","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2818346.2820780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM on International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/123456789/510355","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045185635","display_name":"Punarjay Chakravarty","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Punarjay Chakravarty","raw_affiliation_strings":["KU Leuven - University of Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven - University of Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026428383","display_name":"Sayeh Mirzaei","orcid":"https://orcid.org/0000-0003-1174-2280"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Sayeh Mirzaei","raw_affiliation_strings":["Amirkabir University of Technology, Tehran, Islamic Republic of"],"affiliations":[{"raw_affiliation_string":"Amirkabir University of Technology, Tehran, Islamic Republic of","institution_ids":["https://openalex.org/I158248296"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074816094","display_name":"Tinne Tuytelaars","orcid":"https://orcid.org/0000-0003-3307-9723"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tinne Tuytelaars","raw_affiliation_strings":["KU Leuven - University of Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven - University of Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van hamme","raw_affiliation_strings":["KU Leuven - University of Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven - University of Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045185635"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":1.1488,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.80008162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"90"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9937999844551086,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9932000041007996,"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":0.7446766495704651},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.6150388717651367},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5984559059143066},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5979385375976562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5336421728134155},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49225130677223206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4777052402496338},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4276005029678345},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25611692667007446},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09020853042602539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446766495704651},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.6150388717651367},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5984559059143066},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5979385375976562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5336421728134155},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49225130677223206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4777052402496338},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4276005029678345},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25611692667007446},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09020853042602539},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2818346.2820780","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2818346.2820780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 ACM on International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/510355","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/510355","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"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":"ACM international conference on multimodal interaction - ICMI 2015, Seattle, Washington, USA, 9-13 November 2015","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/510355","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/510355","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"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":"ACM international conference on multimodal interaction - ICMI 2015, Seattle, Washington, USA, 9-13 November 2015","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1606858007","https://openalex.org/W2022699039","https://openalex.org/W2054852564","https://openalex.org/W2066348332","https://openalex.org/W2095309665","https://openalex.org/W2104804886","https://openalex.org/W2105101328","https://openalex.org/W2138761194","https://openalex.org/W2154636774","https://openalex.org/W2394807913","https://openalex.org/W2951552696","https://openalex.org/W6605031968"],"related_works":["https://openalex.org/W107154053","https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2043735059","https://openalex.org/W2149163000"],"abstract_inverted_index":{"Active":[0],"speakers":[1],"have":[2],"traditionally":[3],"been":[4],"identified":[5],"in":[6],"video":[7,58],"by":[8],"detecting":[9],"their":[10],"moving":[11],"lips.":[12],"This":[13],"paper":[14],"demonstrates":[15],"the":[16,29,54],"same":[17],"using":[18,42],"spatio-temporal":[19],"features":[20],"that":[21],"aim":[22],"to":[23,52],"capture":[24],"other":[25],"cues:":[26],"movement":[27],"of":[28,35,56],"head,":[30],"upper":[31],"body":[32],"and":[33],"hands":[34],"active":[36],"speakers.":[37],"Speaker":[38],"directional":[39],"information,":[40],"obtained":[41],"sound":[43],"source":[44],"localization":[45],"from":[46],"a":[47],"microphone":[48],"array":[49],"is":[50],"used":[51],"supervise":[53],"training":[55],"these":[57],"features.":[59]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2016,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
