{"id":"https://openalex.org/W2536165811","doi":"https://doi.org/10.1109/iwaenc.2016.7602903","title":"Modeling audio directional statistics using a probabilistic spatial dictionary for speaker diarization in real meetings","display_name":"Modeling audio directional statistics using a probabilistic spatial dictionary for speaker diarization in real meetings","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2536165811","doi":"https://doi.org/10.1109/iwaenc.2016.7602903","mag":"2536165811"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2016.7602903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2016.7602903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5007282822","display_name":"Mahmoud Fakhry","orcid":"https://orcid.org/0000-0002-2170-2998"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mahmoud Fakhry","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101438174","display_name":"Nobutaka Ito","orcid":"https://orcid.org/0000-0001-9740-6848"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ito","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9039919972419739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7770072221755981},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6217028498649597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5873311758041382},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5119262933731079},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4861745238304138},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4649336040019989},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4430285096168518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42686256766319275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40289491415023804},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10178232192993164}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9039919972419739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770072221755981},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6217028498649597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5873311758041382},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5119262933731079},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4861745238304138},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4649336040019989},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4430285096168518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42686256766319275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40289491415023804},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10178232192993164},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc.2016.7602903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2016.7602903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1514329737","https://openalex.org/W1557470594","https://openalex.org/W1558643924","https://openalex.org/W1991082011","https://openalex.org/W1996160600","https://openalex.org/W2005733316","https://openalex.org/W2012910847","https://openalex.org/W2034049738","https://openalex.org/W2043216213","https://openalex.org/W2081074144","https://openalex.org/W2106310986","https://openalex.org/W2141398670","https://openalex.org/W2145167175","https://openalex.org/W2148613904","https://openalex.org/W2153773386","https://openalex.org/W2338994564","https://openalex.org/W2405521185","https://openalex.org/W3141933106","https://openalex.org/W4300223101","https://openalex.org/W6630627665","https://openalex.org/W6633348054","https://openalex.org/W6653298445","https://openalex.org/W6658954917","https://openalex.org/W6681537870","https://openalex.org/W6713624473"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1521049138","https://openalex.org/W2144208207","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2160753975","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2161543916"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,16],"is":[2,50,115],"the":[3,69,73,80,95,100,103,119],"task":[4],"of":[5,39,45,55,61,72,82],"estimating":[6],"\u201cwho":[7],"spoke":[8],"when\u201d":[9],"in":[10,127],"a":[11,43,83,87,91,112,137],"meeting.":[12],"To":[13,93],"realize":[14],"accurate":[15],"for":[17],"real":[18,128],"meetings,":[19,129],"we":[20,33],"have":[21],"to":[22,35,117,136],"deal":[23],"with":[24,86],"noise,":[25],"speaker":[26,101],"overlap,":[27],"reverberation,":[28],"etc.":[29],"In":[30],"this":[31],"work,":[32],"propose":[34],"model":[36,118],"directional":[37],"statistics":[38],"spatial":[40,53,88],"clusters":[41,97],"via":[42],"dictionary":[44,49],"probabilistic":[46],"models.":[47],"The":[48,122],"trained":[51,74],"using":[52],"features":[54],"possible":[56],"source":[57,63,84],"locations.":[58],"Observed":[59],"mixtures":[60],"multiple":[62],"signals":[64],"are":[65,105],"statistically":[66],"represented":[67],"as":[68],"weighted":[70],"sum":[71],"models,":[75],"where":[76],"each":[77],"weight":[78],"defines":[79],"activity":[81],"associated":[85],"location":[89],"or":[90],"cluster.":[92],"detect":[94],"active":[96],"and":[98,130],"perform":[99],"diarization,":[102],"weights":[104],"estimated":[106],"by":[107],"applying":[108],"Bayes'":[109],"rule.":[110],"Furthermore,":[111],"Laplace":[113],"distribution":[114],"proposed":[116,123],"background":[120],"noise.":[121],"method":[124],"was":[125],"evaluated":[126],"it":[131],"provided":[132],"high":[133],"performance":[134],"comparing":[135],"baseline":[138],"method.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}