{"id":"https://openalex.org/W2040023846","doi":"https://doi.org/10.1109/icassp.2009.4960523","title":"Speaker diarization in meeting audio","display_name":"Speaker diarization in meeting audio","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2040023846","doi":"https://doi.org/10.1109/icassp.2009.4960523","mag":"2040023846"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","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/A5050008407","display_name":"Tin Lay Nwe","orcid":"https://orcid.org/0000-0003-1111-580X"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Tin Lay Nwe","raw_affiliation_strings":["Institute of Infocomm Research (IR), Agency for Science, Technology and Research, Singapore","Institute for Infocomm Research (I2R), A*STAR, 1 Fusionopolis way, Singapore, 138632"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (IR), Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR, 1 Fusionopolis way, Singapore, 138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100813843","display_name":"Hanwu Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwu Sun","raw_affiliation_strings":["Institute of Infocomm Research (IR), Agency for Science, Technology and Research, Singapore","Institute for Infocomm Research (I2R), A*STAR, 1 Fusionopolis way, Singapore, 138632"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (IR), Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR, 1 Fusionopolis way, Singapore, 138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","Institute for Infocomm Research (I2R), A*STAR, 1 Fusionopolis way, Singapore, 138632"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR, 1 Fusionopolis way, Singapore, 138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054558832","display_name":"Susanto Rahardja","orcid":"https://orcid.org/0000-0003-0831-6934"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Susanto Rahardja","raw_affiliation_strings":["Institute of Infocomm Research (IR), Agency for Science, Technology and Research, Singapore","Institute for Infocomm Research (I2R), A*STAR, 1 Fusionopolis way, Singapore, 138632"],"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (IR), Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR, 1 Fusionopolis way, Singapore, 138632","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050008407"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":3.1722,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91631714,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4073","last_page":"4076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9988999962806702,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8504802584648132},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.826174259185791},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.8144961595535278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7875368595123291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7046680450439453},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6067922711372375},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5081226825714111},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5080177783966064},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49354350566864014},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4851008653640747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4810669422149658},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4245501458644867},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4100503921508789},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3512284755706787}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8504802584648132},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.826174259185791},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8144961595535278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875368595123291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7046680450439453},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6067922711372375},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5081226825714111},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5080177783966064},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49354350566864014},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4851008653640747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4810669422149658},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4245501458644867},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4100503921508789},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3512284755706787},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W30000143","https://openalex.org/W87496662","https://openalex.org/W1538482441","https://openalex.org/W1548779692","https://openalex.org/W1574017590","https://openalex.org/W2041823554","https://openalex.org/W2114863372","https://openalex.org/W2148613904","https://openalex.org/W2177650602","https://openalex.org/W2398758317","https://openalex.org/W6634515183"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1197719229","https://openalex.org/W4247736853","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W106647055","https://openalex.org/W1992796048","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"speaker":[3,96],"diarization":[4],"system":[5,67,100],"on":[6],"a":[7,65],"NIST":[8],"Rich":[9],"Transcription":[10],"2007":[11],"(RT-07)":[12],"meeting":[13],"recognition":[14],"evaluation":[15],"data":[16],"set":[17],"for":[18,54,59,79,95],"the":[19,102],"task":[20],"of":[21,44,105],"multiple":[22],"distant":[23],"microphone":[24],"(MDM).":[25],"Our":[26],"implementation":[27],"includes":[28],"three":[29],"components:":[30],"initial":[31],"clustering,":[32],"non-speech":[33,60,80],"removal":[34,61,81],"and":[35,48],"cluster":[36,97],"purification.":[37,98],"Initial":[38],"clusters":[39],"are":[40],"generated":[41],"using":[42,70],"directional":[43],"arrival":[45],"(DOA)":[46],"information":[47,71],"bootstrap":[49],"clustering.":[50],"Multiple":[51],"GMM":[52,90],"modeling":[53],"speech/non-speech":[55],"classification":[56],"is":[57,77,93],"employed":[58,94],"component.":[62,82],"In":[63],"addition,":[64],"novel":[66],"fusion":[68],"strategy":[69],"from":[72],"receiver":[73],"operating":[74],"curve":[75],"(ROC)":[76],"proposed":[78],"Finally,":[83],"consensus":[84],"clustering":[85,91],"approach":[86],"together":[87],"with":[88],"iterative":[89],"method":[92],"The":[99],"achieves":[101],"overall":[103],"DER":[104],"10.81%.":[106]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
