{"id":"https://openalex.org/W2137178960","doi":"https://doi.org/10.1109/icassp.2012.6288984","title":"Determining the number of speakers in a meeting using microphone array features","display_name":"Determining the number of speakers in a meeting using microphone array features","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2137178960","doi":"https://doi.org/10.1109/icassp.2012.6288984","mag":"2137178960"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/7df8915c-6bd6-4cd7-a60a-bf4f9737abce","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080148886","display_name":"Erich Zwyssig","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erich Zwyssig","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","EADS IW, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"EADS IW, Edinburgh, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110108257","display_name":"Mike Lincoln","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mike Lincoln","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4765","last_page":"4768"},"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9941999912261963,"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/multilateration","display_name":"Multilateration","score":0.8689383268356323},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7238277196884155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7023937106132507},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6932182312011719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6373202800750732},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5723962187767029},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5124543309211731},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4558883309364319},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45424023270606995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43080294132232666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37869757413864136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1893620491027832},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0823010802268982}],"concepts":[{"id":"https://openalex.org/C104037064","wikidata":"https://www.wikidata.org/wiki/Q1640884","display_name":"Multilateration","level":3,"score":0.8689383268356323},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7238277196884155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023937106132507},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6932182312011719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6373202800750732},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5723962187767029},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5124543309211731},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4558883309364319},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45424023270606995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43080294132232666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37869757413864136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1893620491027832},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0823010802268982},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2012.6288984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.3527","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.3527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/zwyssig-dia-icassp12.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/7df8915c-6bd6-4cd7-a60a-bf4f9737abce","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7df8915c-6bd6-4cd7-a60a-bf4f9737abce","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Zwyssig, E, Renals, S & Lincoln, M 2012, Determining the number of speakers in a meeting using microphone array features. in Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on. pp. 4765-4768. https://doi.org/10.1109/ICASSP.2012.6288984","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7df8915c-6bd6-4cd7-a60a-bf4f9737abce","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/7df8915c-6bd6-4cd7-a60a-bf4f9737abce","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"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":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/7df8915c-6bd6-4cd7-a60a-bf4f9737abce","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7df8915c-6bd6-4cd7-a60a-bf4f9737abce","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Zwyssig, E, Renals, S & Lincoln, M 2012, Determining the number of speakers in a meeting using microphone array features. in Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on. pp. 4765-4768. https://doi.org/10.1109/ICASSP.2012.6288984","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W41021157","https://openalex.org/W90546637","https://openalex.org/W1424447973","https://openalex.org/W1482605500","https://openalex.org/W1515932869","https://openalex.org/W1517146827","https://openalex.org/W1556474518","https://openalex.org/W1988540447","https://openalex.org/W2046317813","https://openalex.org/W2098726438","https://openalex.org/W2113386290","https://openalex.org/W2114863372","https://openalex.org/W2129120544","https://openalex.org/W2148613904","https://openalex.org/W2153842971","https://openalex.org/W3007258144","https://openalex.org/W3105118415","https://openalex.org/W6601719842","https://openalex.org/W6603701099","https://openalex.org/W6628438334","https://openalex.org/W6628911050","https://openalex.org/W6630906535","https://openalex.org/W6773633977"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2188292175","https://openalex.org/W2385053527","https://openalex.org/W4386900535","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2900122540"],"abstract_inverted_index":{"The":[0],"accuracy":[1],"of":[2,14,28,39,66,83,89],"speaker":[3,49,74],"diarisation":[4],"in":[5,42,127],"meetings":[6],"relies":[7],"heavily":[8],"on":[9,25],"determining":[10],"the":[11,36,48,58,67,80,87,90,117],"correct":[12,37,81],"number":[13,38,82],"speakers.":[15],"In":[16,95],"this":[17],"paper":[18],"we":[19,78,97],"present":[20],"a":[21,43,73],"novel":[22],"algorithm":[23],"based":[24],"time":[26],"difference":[27],"arrival":[29],"(TDOA)":[30],"features":[31],"that":[32],"aims":[33],"to":[34,71],"find":[35],"active":[40,84],"speakers":[41,85],"meeting":[44,111],"and":[45,51,63,106,121,125],"thus":[46],"aid":[47,88],"segmentation":[50],"clustering":[52],"process.":[53],"With":[54],"our":[55],"proposed":[56],"method":[57],"microphone":[59],"array":[60,68],"TDOA":[61],"values":[62],"known":[64],"geometry":[65],"are":[69],"used":[70],"calculate":[72],"matrix":[75],"from":[76],"which":[77],"determine":[79],"with":[86,132],"Bayesian":[91],"information":[92],"criterion":[93],"(BIC).":[94],"addition,":[96],"analyse":[98],"several":[99],"well-known":[100],"voice":[101],"activity":[102],"detection":[103],"(VAD)":[104],"algorithms":[105],"verified":[107],"their":[108],"fitness":[109],"for":[110],"recordings.":[112],"Experiments":[113],"were":[114],"performed":[115],"using":[116],"NIST":[118],"RT06,":[119],"RT07":[120],"RT09":[122],"data":[123],"sets,":[124],"resulted":[126],"reduced":[128],"error":[129],"rates":[130],"compared":[131],"BIC-based":[133],"approaches.":[134]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}