{"id":"https://openalex.org/W2161176017","doi":"https://doi.org/10.1109/icme.2005.1521688","title":"Speech Acquisition in Meetings with an Audio-Visual Sensor Array","display_name":"Speech Acquisition in Meetings with an Audio-Visual Sensor Array","publication_year":2005,"publication_date":"2005-10-24","ids":{"openalex":"https://openalex.org/W2161176017","doi":"https://doi.org/10.1109/icme.2005.1521688","mag":"2161176017"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2005.1521688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/83185","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072372659","display_name":"Iain McCowan","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"I. McCowan","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080465815","display_name":"M.H. Krishna","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"M.H. Krishna","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012965551","display_name":"Daniel G\u00e1tica-P\u00e9rez","orcid":"https://orcid.org/0000-0001-5488-2182"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"D. Gatica-Perez","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101490729","display_name":"David Moore","orcid":"https://orcid.org/0009-0000-8340-3013"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"D. Moore","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037326211","display_name":"Sil\u00e8ye Ba","orcid":"https://orcid.org/0000-0003-4581-9880"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sileye Ba","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1382","last_page":"1385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.9036197066307068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7470515966415405},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6421738862991333},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6419731378555298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6128743290901184},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5203658938407898},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48525047302246094},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.44811728596687317},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4424741566181183},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4419053792953491},{"id":"https://openalex.org/keywords/noise-canceling-microphone","display_name":"Noise-canceling microphone","score":0.4387950599193573},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43580162525177},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4275183379650116},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4156535267829895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2840551733970642},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.21154281497001648},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12012577056884766}],"concepts":[{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.9036197066307068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470515966415405},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6421738862991333},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6419731378555298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6128743290901184},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5203658938407898},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48525047302246094},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.44811728596687317},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4424741566181183},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4419053792953491},{"id":"https://openalex.org/C36922181","wikidata":"https://www.wikidata.org/wiki/Q7047650","display_name":"Noise-canceling microphone","level":5,"score":0.4387950599193573},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43580162525177},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4275183379650116},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4156535267829895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2840551733970642},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.21154281497001648},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12012577056884766},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":4,"locations":[{"id":"doi:10.1109/icme.2005.1521688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.4415","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.4415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.idiap.ch/~gatica/publications/McCowanKrishnaGaticaMooreBa-icme05.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:83185","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83185","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:83310","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83310","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:83185","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83185","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W44831635","https://openalex.org/W1493595169","https://openalex.org/W1528004142","https://openalex.org/W1558276682","https://openalex.org/W1931312565","https://openalex.org/W1992989752","https://openalex.org/W2033819227","https://openalex.org/W2046845112","https://openalex.org/W2071795835","https://openalex.org/W2093225945","https://openalex.org/W2095614026","https://openalex.org/W2116623987","https://openalex.org/W2123993331","https://openalex.org/W2149693148","https://openalex.org/W6629645474","https://openalex.org/W6631246523"],"related_works":["https://openalex.org/W2171964103","https://openalex.org/W2122951924","https://openalex.org/W2092524451","https://openalex.org/W2357486315","https://openalex.org/W2290630525","https://openalex.org/W42422348","https://openalex.org/W2388820283","https://openalex.org/W2106234373","https://openalex.org/W2553243520","https://openalex.org/W1515932869"],"abstract_inverted_index":{"Close-talk":[0],"headset":[1],"microphones":[2],"have":[3],"been":[4],"traditionally":[5],"used":[6],"for":[7,25,51,91,106,120],"speech":[8,95,121,132],"acquisition":[9],"in":[10,33,97],"a":[11,19,62,81,87,118],"number":[12],"of":[13,55,74,80,89,114,129],"applications,":[14],"as":[15,48],"they":[16,49],"naturally":[17],"provide":[18],"higher":[20],"signal-to-noise":[21],"ratio":[22],"-":[23],"needed":[24],"recognition":[26],"tasks":[27],"than":[28],"single":[29,140],"distant":[30],"microphones.":[31,144],"However,":[32],"multi-party":[34],"conversational":[35],"settings":[36],"like":[37],"meetings,":[38],"microphone":[39,84],"arrays":[40],"represent":[41],"an":[42,75],"important":[43],"alternative":[44],"to":[45,136],"close-talking":[46,141],"microphones,":[47],"allow":[50],"localisation":[52],"and":[53,57,86,94,104,109,125,142],"tracking":[54,93],"speakers":[56],"signal-independent":[58],"enhancement,":[59],"while":[60],"providing":[61],"non-intrusive,":[63],"hands-free":[64],"operation":[65],"mode.":[66],"In":[67],"this":[68],"article,":[69],"we":[70],"investigate":[71],"the":[72,112,115,127,130],"use":[73],"audio-visual":[76],"sensor":[77],"array,":[78],"composed":[79],"small":[82],"table-top":[83,143],"array":[85],"set":[88],"cameras,":[90],"speaker":[92],"enhancement":[96],"meetings.":[98],"Our":[99],"methodology":[100],"first":[101],"fuses":[102],"audio":[103],"video":[105],"person":[107],"tracking,":[108],"then":[110],"integrates":[111],"output":[113],"tracker":[116],"with":[117,134],"beamformer":[119],"enhancement.":[122],"We":[123],"compare":[124],"discuss":[126],"features":[128],"resulting":[131],"signal":[133],"respect":[135],"that":[137],"obtained":[138],"from":[139]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
