{"id":"https://openalex.org/W2060656758","doi":"https://doi.org/10.1109/icassp.2010.5495077","title":"Speaker diarization system for RT07 and RT09 meeting room audio","display_name":"Speaker diarization system for RT07 and RT09 meeting room audio","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2060656758","doi":"https://doi.org/10.1109/icassp.2010.5495077","mag":"2060656758"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/A5100813843","display_name":"Hanwu Sun","orcid":null},"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":"Hanwu Sun","raw_affiliation_strings":["Institute for Infocomm Research (IR), ASTAR (Agency for Science, Technology & Research), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (IR), ASTAR (Agency for Science, Technology & Research), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"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":"Bin Ma","raw_affiliation_strings":["Institute for Infocomm Research (IR), ASTAR (Agency for Science, Technology & Research), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (IR), ASTAR (Agency for Science, Technology & Research), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047424296","display_name":"Swe Zin Kalayar Khine","orcid":null},"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":"Swe Zin Kalayar Khine","raw_affiliation_strings":["Institute for Infocomm Research (IR), ASTAR (Agency for Science, Technology & Research), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (IR), ASTAR (Agency for Science, Technology & Research), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","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"]},{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Computer Science and Statistics, University of Eastern Finland, Joensuu, Finland","Institute for Infocomm Research (IR), ASTAR (Agency for Science, Technology & Research), Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Statistics, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"Institute for Infocomm Research (IR), ASTAR (Agency for Science, Technology & Research), Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100813843"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":7.432,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.97015738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4982","last_page":"4985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/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":0.9991999864578247,"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":0.9661965370178223},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7912791967391968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773806631565094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7306918501853943},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6523370146751404},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6128227710723877},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5636777281761169},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5476226210594177},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5125312805175781},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4768563210964203},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.46349358558654785},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43444162607192993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37544524669647217},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11493808031082153},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09127086400985718}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9661965370178223},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7912791967391968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773806631565094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7306918501853943},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6523370146751404},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6128227710723877},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5636777281761169},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5476226210594177},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5125312805175781},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4768563210964203},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.46349358558654785},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43444162607192993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37544524669647217},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11493808031082153},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09127086400985718},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.869.8849","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.869.8849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mirlab.org/conference_papers/International_Conference/ICASSP%202010/pdfs/0004982.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W41021157","https://openalex.org/W90546637","https://openalex.org/W1876378865","https://openalex.org/W2041823554","https://openalex.org/W2101025008","https://openalex.org/W2106015547","https://openalex.org/W2114863372","https://openalex.org/W2216290105","https://openalex.org/W2338994564","https://openalex.org/W3129653033","https://openalex.org/W6601719842"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2099333848"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3],"improved":[4],"speaker":[5,35,117,125],"diarization":[6,118,126],"system":[7,27,107],"for":[8,47,102,114,122],"the":[9,16,44,48,70,78,90,93,97,103],"Single":[10],"Distant":[11],"Microphone":[12],"(SDM)":[13],"task":[14,119],"in":[15],"2007":[17],"and":[18,37,52,96,120],"2009":[19],"NIST":[20],"Rich":[21],"Transcription":[22],"Meeting":[23],"Recognition":[24],"Evaluations.":[25],"The":[26,40,106],"includes":[28],"three":[29],"main":[30],"modules:":[31],"front-end":[32,41],"processing,":[33],"initial":[34,79],"clustering":[36],"cluster":[38,104],"purification/merging.":[39],"processing":[42],"involves":[43],"Wiener":[45],"filtering":[46],"targeted":[49],"audio":[50],"channels":[51],"a":[53],"self-adaptation":[54],"speech":[55],"activity":[56],"detection":[57],"algorithm.":[58],"A":[59],"simple":[60],"but":[61],"effective":[62],"energy":[63],"based":[64],"segmentation":[65],"is":[66,85,100],"applied":[67],"to":[68,76,87],"chunk":[69],"meeting":[71],"data":[72],"into":[73],"small":[74],"segments":[75],"construct":[77],"clusters.":[80],"An":[81],"enhanced":[82],"purification":[83],"algorithm":[84],"proposed":[86],"further":[88],"improve":[89],"performance":[91],"after":[92],"preliminary":[94],"purification,":[95],"BIC":[98],"criterion":[99],"adopted":[101],"merging.":[105],"achieves":[108],"competitive":[109],"overall":[110],"DERs":[111],"of":[112],"15.67%":[113],"RT07":[115],"SDM":[116,124],"17.34%":[121],"RT09":[123],"task.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"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":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
