{"id":"https://openalex.org/W2767042273","doi":"https://doi.org/10.23919/eusipco.2017.8081391","title":"Data-driven and physical model-based designs of probabilistic spatial dictionary for online meeting diarization and adaptive beamforming","display_name":"Data-driven and physical model-based designs of probabilistic spatial dictionary for online meeting diarization and adaptive beamforming","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2767042273","doi":"https://doi.org/10.23919/eusipco.2017.8081391","mag":"2767042273"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2017.8081391","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th European Signal Processing Conference (EUSIPCO)","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/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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 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":"20","issue":null,"first_page":"1165","last_page":"1169"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7982833385467529},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6110451817512512},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5917476415634155},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5823379755020142},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5801787376403809},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5708096623420715},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5016078948974609},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.49387413263320923},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.488372266292572},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45971444249153137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4454626441001892},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3978148102760315},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.19179204106330872},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07427969574928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982833385467529},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6110451817512512},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5917476415634155},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5823379755020142},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5801787376403809},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5708096623420715},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5016078948974609},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.49387413263320923},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.488372266292572},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45971444249153137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4454626441001892},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3978148102760315},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.19179204106330872},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07427969574928284},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":1,"locations":[{"id":"doi:10.23919/eusipco.2017.8081391","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2017.8081391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1506558619","https://openalex.org/W1934041838","https://openalex.org/W1991082011","https://openalex.org/W2005733316","https://openalex.org/W2012910847","https://openalex.org/W2031583051","https://openalex.org/W2042860487","https://openalex.org/W2043216213","https://openalex.org/W2125586671","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2394967684","https://openalex.org/W2398042854","https://openalex.org/W2714509385","https://openalex.org/W4249052411","https://openalex.org/W6651792828","https://openalex.org/W6711908631"],"related_works":["https://openalex.org/W818226659","https://openalex.org/W2996333928","https://openalex.org/W2009075871","https://openalex.org/W2132841313","https://openalex.org/W2518591292","https://openalex.org/W1976800395","https://openalex.org/W2105408150","https://openalex.org/W2606661315","https://openalex.org/W2548445082","https://openalex.org/W2072054645"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,59],"comparatively":[4],"study":[5],"alternative":[6],"dictionary":[7,24,47,79,98],"designs":[8,65],"for":[9,29,43,94],"recently":[10],"proposed":[11],"meeting":[12,72],"diarization":[13],"and":[14,39,62],"adaptive":[15],"beamforming":[16],"based":[17],"on":[18,70],"a":[19,71,76,81,104],"probabilistic":[20],"spatial":[21],"dictionary.":[22,68],"This":[23],"models":[25],"the":[26,40,67,95,101,108,116,125,128],"feature":[27,41],"distribution":[28,42],"each":[30],"possible":[31],"direction":[32],"of":[33,36,66,86,119,127],"arrival":[34],"(DOA)":[35],"speech":[37,130],"signals":[38],"background":[44],"noise.":[45],"The":[46],"enables":[48,55],"online":[49,56],"DOA":[50],"detection,":[51],"which":[52,89],"in":[53],"turn":[54],"diarization.":[57],"Here":[58],"describe":[60],"data-driven":[61,97],"physical":[63,77],"model-based":[64,78],"Experiments":[69],"dataset":[73],"showed":[74],"that":[75,93,110],"gave":[80],"word":[82],"error":[83],"rate":[84],"(WER)":[85],"24.9":[87],"%,":[88],"is":[90],"close":[91],"to":[92,114],"best-performing":[96],"(24.1%).":[99],"Therefore,":[100],"former":[102],"has":[103],"significant":[105],"advantage":[106],"over":[107],"latter":[109],"it":[111],"allows":[112],"us":[113],"bypass":[115],"cumbersome":[117],"measurement":[118],"training":[120],"data":[121],"without":[122],"much":[123],"degrading":[124],"performance":[126],"automatic":[129],"recognition":[131],"(ASR).":[132]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}